[R] arrangement of crowded labels
Dear R users I'm looking for algorithms that assist in spreading out crowded labels, e.g. labels of points in a scatter plot, in order to obtain a nicer visual appearance and better legibility. I'm probably just stuck because I didn't find the right key words for a successful search on the R websites or in the mailing list archives. Any hints are appreciated. Thomas Zumbrunn University of Basel __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] arrangement of crowded labels
I'm looking for algorithms that assist in spreading out crowded labels, e.g. labels of points in a scatter plot, in order to obtain a nicer visual appearance and better legibility. I'm probably just stuck because I didn't find the right key words for a successful search on the R websites or in the mailing list archives. Try thigmophobe.labels in the plotrix package. Regards, Richie. Mathematical Sciences Unit HSL ATTENTION: This message contains privileged and confidential inform...{{dropped:20}} __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] nlrwr package. Error when fitting the optimal Box-Cox transformation with two variables
El mar, 19-05-2009 a las 17:17 +0200, Ikerne del Valle escribió: Dear all: I'm trying to fit the optimal Box-Cox transformation related to nls (see the code below) for the demand of money data in Green (3th Edition) but in the last step R gives the next error message. Error en `[.data.frame`(eval(object$data), , as.character(formula(object)[[2]])[2]) : undefined columns selected. ¿Any idea to solve the problem? Thanks in advance, library(nlrwr) r-c(4.50,4.19,5.16,5.87,5.95,4.88,4.50,6.44,7.83,6.25,5.50,5.46,7.46,10.28,11.77,13.42,11.02,8.50,8.80,7.69) M-c(480.00,524.30,566.30,589.50,628.20,712.80,805.20,861.00,908.40,1023.10,1163.60,1286.60,1388.90,1497.90,1631.40,1794.40,1954.90,2188.80,2371.70,2563.60) Y-c(2208.30,2271.40,2365.60,2423.30,2416.20,2484.80,2608.50,2744.10,2729.30,2695.00,2826.70,2958.60,3115.20,3192.40,3187.10,3248.80,3166.00,3277.70,3492.00,3573.50) money-data.frame(r,M,Y) attach(money) ols1-lm(log(M)~log(r)+log(Y)) output1-summary(ols1) coef1-ols1$coefficients a1-coef1[[1]] b11-coef1[[2]] b21-coef1[[3]] money.m1-nls(log(M)~a+b*r^g+c*Y^g,data=money,start=list(a=a1,b=b11,g=1,c=b21)) summary(money.m1) money.m2-boxcox(money.m1) Prof. Ikerne del Valle Erkiaga Department of Applied Economics V Faculty of Economic and Business Sciences University of the Basque Country Avda. Lehendakari Agirre, Nº 83 48015 Bilbao (Bizkaia) Spain Ikerne, Inside boxcox.nls, the variable log(M) is searched in dataframe money and not found. Indeed, it is a little redundant to take logs and then search a Box-Cox transformation --which gives the log when lambda is zero. If you really want to do that, you might define a new variable logM and include that in your money dataframe, then rewrite the nls() call as: money.m1 - nls(logM ~ a + b ... etc. Best, ft. -- Fernando TUSELLe-mail: Departamento de Econometría y Estadística fernando.tus...@ehu.es Facultad de CC.EE. y Empresariales Tel: (+34)94.601.3733 Universidad del País Vasco Secr: (+34)94.601.3740 Avenida Lendakari Aguirre, 83 Fax: (+34)94.601.3754 E-48015 BILBAO (Spain) http://www.et.bs.ehu.es/~etptupaf __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Running multiple versions of Rserve on a Linux system
Hi useRs, I would like to know how to run two versions of Rserve on a Linux system. I am using the old JRE client of Rserve which requires me to use Rserve version 0.4-3. I am also using the new REngine API to connect to Rserve version 0.6. I would like to run both these Rserve versions on a Linux system. Is it necessary that I install two versions of R, and install these two Rserve versions in each R installation? I am aware that one can use multiple config files and provide different port numbers, but that would run the same version of Rserve with different settings. - Install the two Rserve versions in the same R installation. Must I provide an alternate library location for the other Rserve version to be installed into? - Install two R versions and install the two Rserve versions in each R installation? Any help in this regard will be much appreciated. Thanks Harsh Singhal [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Package Inline under windows
_ wrote: Hi all, I installed the package inline (windows-version) but can not compile any code, I alway get an error message ERROR(s) during compilation : source code errors or compiler configuration errors! Unfornutanely there is no description where the package finds a c-compiler nor where so set the configuration. Using the linux version, everything works. There's nothing special about it: just follow the instructions in Appendix E of the R Installation and Administration manual for setting up the tools. Duncan Murdoch __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Functions returning functions
Dear All: I have a question regarding the behavior of functions. Say I define a function that returns another function : A - function(parameters) { # calculations w/ parameters returning 'y' tmpf - function(x) { # function of 'y' } return(tmpf) } The value of the parameters are stored in an environment local to the function. Then I call x- something B-A(x) When R executes this last statement, does it perform all the calculations inside function A again (i.e., all the calculations that yield 'y') or the value of 'y' is already stored in the function's local environment ? Many thanks. Paulo Gustavo Grahl, CFA __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] *** POSSIBLE SPAM *** Functions returning functions
Paulo Grahl wrote: Dear All: I have a question regarding the behavior of functions. Say I define a function that returns another function : A - function(parameters) { # calculations w/ parameters returning 'y' tmpf - function(x) { # function of 'y' } return(tmpf) } The value of the parameters are stored in an environment local to the function. Then I call x- something B-A(x) When R executes this last statement, does it perform all the calculations inside function A again no, see this: f - function( x = 3){ +function( ){} + } g - f() ls.str( environment(g) ) x : num 3 h - f(6) ls.str( environment(h) ) x : num 6 ls.str( environment(g) ) x : num 3 See also colorRampPalette which uses this feature: colorRampPalette function (colors, ...) { ramp - colorRamp(colors, ...) function(n) { x - ramp(seq.int(0, 1, length.out = n)) rgb(x[, 1], x[, 2], x[, 3], maxColorValue = 255) } } environment: namespace:grDevices pal - colorRampPalette( c(blue, white, red) ) pal function (n) { x - ramp(seq.int(0, 1, length.out = n)) rgb(x[, 1], x[, 2], x[, 3], maxColorValue = 255) } environment: 0x99aba4c ls.str( environment( pal ) ) colors : chr [1:3] blue white red ramp : function (x) (i.e., all the calculations that yield 'y') or the value of 'y' is already stored in the function's local environment ? Many thanks. Paulo Gustavo Grahl, CFA -- Romain Francois Independent R Consultant +33(0) 6 28 91 30 30 http://romainfrancois.blog.free.fr __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] SEM:Standard error of std.coef estimates?
Hi, I am currently working with the sem package in R, to create pathway diagrams. Id like to use the standardized path coeffcients. To get these, I use std.coef. However, using this yields only the standardized coefficients, but does not give me the standard error. Does someone know how to get std.coef to show the standard error of the standardized path coefficients as well? Thanks, Bastiaan PS: When I use std.coef, all I get is this: std.coef(path.model.SSI4) Std. Estimate par1 par1 0.39499 com_veg --- tempm par2 par2 0.35231 SNutBili --- tempm par3 par3 -0.68170 S_SSI4 --- tempm par4 par4 -0.39145 com_veg --- Wdeficit par5 par5 -0.60025 SNutBili --- Wdeficit par6 par6 -0.20562 S_SSI4 --- Wdeficit par7 par7 0.14871 SNutBili --- com_veg par8 par8 0.14905 S_SSI4 --- com_veg par9 par9 -0.39164 S_SSI4 --- SNutBili -- View this message in context: http://www.nabble.com/SEM%3AStandard-error-of-std.coef-estimates--tp23633227p23633227.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Too large a data set to be handled by R?
If your 1500 X 2 matrix is all numeric, it should take up about 240MB of memory. That should easily fit within the 2GB of your laptop and still leave room for several copies that might arise during the processing. Exactly what are you going to be doing with the data? A lot will depend on the functions/procedures that you will be calling, or the type of transformations you might be doing. On Tue, May 19, 2009 at 11:59 PM, tsunhin wong thjw...@gmail.com wrote: Dear R users, I have been using a dynamic data extraction from raw files strategy at the moment, but it takes a long long time. In order to save time, I am planning to generate a data set of size 1500 x 2 with each data point a 9-digit decimal number, in order to save my time. I know R is limited to 2^31-1 and that my data set is not going to exceed this limit. But my laptop only has 2 Gb and is running 32-bit Windows / XP or Vista. I ran into R memory problem issue before. Please let me know your opinion according to your experience. Thanks a lot! - John __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.htmlhttp://www.r-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Jim Holtman Cincinnati, OH +1 513 646 9390 What is the problem that you are trying to solve? [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] how to calculate means of matrix elements
In that case use a modification of Jim's solution: a - array(cbind(mat1, mat2, mat3), c(3, 3, 3)) apply(a, 1:2, mean, na.rm = TRUE) On Tue, May 19, 2009 at 8:49 AM, dxc13 dx...@health.state.ny.us wrote: Easy enough. What if some of the matrix elements contained missing values? Then how could you still calculate the means? Example code below: mat1 - matrix(c(1,2,3,4,5,NA,7,8,9),3,3) mat2 - matrix(c(NA,6,1,9,0,5,8,2,7),3,3) mat3 - matrix(c(5,9,1,8,NA,3,7,2,4),3,3) Gabor Grothendieck wrote: Try this: (mat1 + mat2 + mat3) / 3 On Mon, May 18, 2009 at 8:40 PM, dxc13 dx...@health.state.ny.us wrote: useR's, I have several matrices of size 4x4 that I want to calculate means of their respective positions with. For example, consider I have 3 matrices given by the code: mat1 - matrix(sample(1:20,16,replace=T),4,4) mat2 - matrix(sample(-5:15,16,replace=T),4,4) mat3 - matrix(sample(5:25,16,replace=T),4,4) The result I want is one matrix of size 4x4 in which position [1,1] is the mean of position [1,1] of the given three matrices. The same goes for all other positions of the matrix. If these three matrices are given in separate text files, how can I write code that will get this result I need? Thanks in advance, dxc13 -- View this message in context: http://www.nabble.com/how-to-calculate-means-of-matrix-elements-tp23607694p23607694.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/how-to-calculate-means-of-matrix-elements-tp23607694p23615755.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Functions returning functions
Paulo Grahl wrote: Dear All: I have a question regarding the behavior of functions. Say I define a function that returns another function : A - function(parameters) { # calculations w/ parameters returning 'y' tmpf - function(x) { # function of 'y' } return(tmpf) } The value of the parameters are stored in an environment local to the function. consider this example: foo = function(a, b) function(c) if (c) a else b x = 1 y = 2 bar = foo(x, y) bar(TRUE) # 1 x = 0 bar(TRUE) # 1, not 0 y = 0 bar(FALSE) # 0, not 2 vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Where to find a changelog for the survival package
Dear All, since some days I try to use the versions 2.35-4 of the survival package instead of versions 2.31, I had installed until now. Several changes in print.survfit, plot.survfit and seemingly in the structure of ratetabels effect some of my syntax files. Is there somewhere a documentation of these changes, besides the code itself? Thanks in advance, Heinz __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Functions returning functions
On Wed, May 20, 2009 at 7:48 AM, Wacek Kusnierczyk waclaw.marcin.kusnierc...@idi.ntnu.no wrote: Paulo Grahl wrote: Dear All: I have a question regarding the behavior of functions. Say I define a function that returns another function : A - function(parameters) { # calculations w/ parameters returning 'y' tmpf - function(x) { # function of 'y' } return(tmpf) } The value of the parameters are stored in an environment local to the function. consider this example: foo = function(a, b) function(c) if (c) a else b x = 1 y = 2 bar = foo(x, y) bar(TRUE) # 1 x = 0 bar(TRUE) # 1, not 0 y = 0 bar(FALSE) # 0, not 2 The last one is due to lazy evaluation. Try repeating it with this variation: foo2 = function(a, b) { force(a); force(b) function(c) if (c) a else b } which forces a and b to be evaluated right away. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Functions returning functions
Romain Francois wrote: Paulo Grahl wrote: Dear All: I have a question regarding the behavior of functions. Say I define a function that returns another function : A - function(parameters) { # calculations w/ parameters returning 'y' tmpf - function(x) { # function of 'y' } return(tmpf) } The value of the parameters are stored in an environment local to the function. Then I call x- something B-A(x) When R executes this last statement, does it perform all the calculations inside function A again no ... but there are ways around it f - function( x = 3 ){ # y will be get a value the first time # the function created below is called delayedAssign( y, { cat( \nevaluating `y` right now\n ) x + 5 } ) # z will get a new value each time the function # created below is called makeActiveBinding( z, function( data ){ if( missing(data) ){ cat( \nevaluating `z` right now\n ) rnorm(x) } }, environment() ) function( ){ list( y, z ) } } h - f() h() evaluating `y` right now evaluating `z` right now [[1]] [1] 8 [[2]] [1] 1.0991189 -1.1033016 -0.5410733 h() evaluating `z` right now [[1]] [1] 8 [[2]] [1] 0.7102276 -0.6371956 -0.7703179 environment(h)[[z]] evaluating `z` right now [1] -0.6713595 2.2006114 0.9335674 environment(h)[[z]] evaluating `z` right now [1] 0.1243523 0.6178176 -0.9043380 see this: f - function( x = 3){ +function( ){} + } g - f() ls.str( environment(g) ) x : num 3 h - f(6) ls.str( environment(h) ) x : num 6 ls.str( environment(g) ) x : num 3 See also colorRampPalette which uses this feature: colorRampPalette function (colors, ...) { ramp - colorRamp(colors, ...) function(n) { x - ramp(seq.int(0, 1, length.out = n)) rgb(x[, 1], x[, 2], x[, 3], maxColorValue = 255) } } environment: namespace:grDevices pal - colorRampPalette( c(blue, white, red) ) pal function (n) { x - ramp(seq.int(0, 1, length.out = n)) rgb(x[, 1], x[, 2], x[, 3], maxColorValue = 255) } environment: 0x99aba4c ls.str( environment( pal ) ) colors : chr [1:3] blue white red ramp : function (x) (i.e., all the calculations that yield 'y') or the value of 'y' is already stored in the function's local environment ? Many thanks. Paulo Gustavo Grahl, CFA -- Romain Francois Independent R Consultant +33(0) 6 28 91 30 30 http://romainfrancois.blog.free.fr __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] turning off specific types of warnings
Dear R users, I have a long function that among other things uses the survest function from the Design package. This function generates the warning: In survest.cph (...) S.E. and confidence intervals are approximate except at predictor means. Use cph(...,x=T,y=T) (and don't use linear.predictors=) for better estimates. I would like to turn this specific warning off, as it makes it difficult to detect other (potentially more crucial) warnings generated by other parts of my code. Is there a way to do this? Eleni Rapsomaniki Research Associate Strangeways Research Laboratory Department of Public Health and Primary Care University of Cambridge __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] turning off specific types of warnings
?suppressWarnings On Wed, May 20, 2009 at 8:10 AM, Eleni Rapsomaniki er...@medschl.cam.ac.ukwrote: Dear R users, I have a long function that among other things uses the survest function from the Design package. This function generates the warning: In survest.cph (...) S.E. and confidence intervals are approximate except at predictor means. Use cph(...,x=T,y=T) (and don't use linear.predictors=) for better estimates. I would like to turn this specific warning off, as it makes it difficult to detect other (potentially more crucial) warnings generated by other parts of my code. Is there a way to do this? Eleni Rapsomaniki Research Associate Strangeways Research Laboratory Department of Public Health and Primary Care University of Cambridge __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.htmlhttp://www.r-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Jim Holtman Cincinnati, OH +1 513 646 9390 What is the problem that you are trying to solve? [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] turning off specific types of warnings
jim holtman wrote: ?suppressWarnings Note that this removes __all__ warnings, if you only want to remove specific warnings, you can adapt suppressWarnings like this: h - function(w) if( any(grepl(ouch, w))) invokeRestart(muffleWarning) withCallingHandlers( warning(ouch), warning = h ) withCallingHandlers( warning(something else), warning = h ) Warning message: In withCallingHandlers(warning(something else), warning = h) : something else Maybe it would make sense to extend suppressWarnings in this direction Romain On Wed, May 20, 2009 at 8:10 AM, Eleni Rapsomaniki er...@medschl.cam.ac.ukwrote: Dear R users, I have a long function that among other things uses the survest function from the Design package. This function generates the warning: In survest.cph (...) S.E. and confidence intervals are approximate except at predictor means. Use cph(...,x=T,y=T) (and don't use linear.predictors=) for better estimates. I would like to turn this specific warning off, as it makes it difficult to detect other (potentially more crucial) warnings generated by other parts of my code. Is there a way to do this? Eleni Rapsomaniki Research Associate Strangeways Research Laboratory Department of Public Health and Primary Care University of Cambridge -- Romain Francois Independent R Consultant +33(0) 6 28 91 30 30 http://romainfrancois.blog.free.fr __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Functions returning functions
Thanks a lot ! regards, Paulo Gustavo Grahl, CFA On Wed, May 20, 2009 at 8:31 AM, Romain Francois romain.franc...@dbmail.com wrote: Paulo Grahl wrote: Dear All: I have a question regarding the behavior of functions. Say I define a function that returns another function : A - function(parameters) { # calculations w/ parameters returning 'y' tmpf - function(x) { # function of 'y' } return(tmpf) } The value of the parameters are stored in an environment local to the function. Then I call x- something B-A(x) When R executes this last statement, does it perform all the calculations inside function A again no, see this: f - function( x = 3){ + function( ){} + } g - f() ls.str( environment(g) ) x : num 3 h - f(6) ls.str( environment(h) ) x : num 6 ls.str( environment(g) ) x : num 3 See also colorRampPalette which uses this feature: colorRampPalette function (colors, ...) { ramp - colorRamp(colors, ...) function(n) { x - ramp(seq.int(0, 1, length.out = n)) rgb(x[, 1], x[, 2], x[, 3], maxColorValue = 255) } } environment: namespace:grDevices pal - colorRampPalette( c(blue, white, red) ) pal function (n) { x - ramp(seq.int(0, 1, length.out = n)) rgb(x[, 1], x[, 2], x[, 3], maxColorValue = 255) } environment: 0x99aba4c ls.str( environment( pal ) ) colors : chr [1:3] blue white red ramp : function (x) (i.e., all the calculations that yield 'y') or the value of 'y' is already stored in the function's local environment ? Many thanks. Paulo Gustavo Grahl, CFA -- Romain Francois Independent R Consultant +33(0) 6 28 91 30 30 http://romainfrancois.blog.free.fr __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] how to merge replicate spots
Hi, Does anybody know how to merge replicate spots in R Bioconductor? I use home-made spotted arrays and every probe is printed in triplicate. I normalize my data using limma package and I do not know how to get mean from these three replicates. Regards, Barbara Cegielska __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Extracting correlation in a nlme model
Hello, for calculation of intraclass correlation coefficient for a simple Random Intercept model, the function ICC1.lme() in the package psychometric can be applied. Best regards, Christine Adrion Kenneth Roy Cabrera Torres wrote: Hi R users: Is there a function to obtain the correlation within groups from this very simple lme model? modeloMx1 Linear mixed-effects model fit by REML Data: barrag Log-restricted-likelihood: -70.92739 Fixed: fza_tension ~ 1 (Intercept) 90.86667 Random effects: Formula: ~1 | molde (Intercept) Residual StdDev:2.610052 2.412176 Number of Observations: 30 Number of Groups: 3 I want to obtain \rho = \sigma_b^2 / (\sigma_b^2 + \sigma^2) I know that I obtain \sigma_b^2 and \sigma^2 with VarCorr(modeloMx1) molde = pdLogChol(1) Variance StdDev (Intercept) 6.812374 2.610052 Residual5.818593 2.412176 But, I want to know if I can obtain \rho = 6.8123/(6.8123 + 5.8185) = 0.53934 straightforward. Thank you for you help. Kenneth __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. - Christine Adrion, Dipl.-Stat., MPH Ludwig-Maximilians-Universitaet Muenchen IBE â Institut für Medizinische Informations- verarbeitung, Biometrie und Epidemiologie Marchioninistr. 15 81377 Muenchen GERMANY Tel.: +49 (0)89 7095-4483 eMail: adr...@ibe.med.uni-muenchen.de Internet: http://ibe.web.med.uni-muenchen.de -- View this message in context: http://www.nabble.com/Extracting-correlation-in-a-nlme-model-tp23628854p23632075.html Sent from the R help mailing list archive at Nabble.com. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Least-square support vector machines regression!
Dear Max, thanks for your valuable comment. I assume that you used the function for regression - not classification. I use Mac OS X plattform (version 10.5.6). The R version is 2.8.1 (I prefer to update to 2.9.1 not 2.9.0). The kernlab package version is 0.9-8. The x and y-input into LSSVM regression can be reproduced by: x-- matrix (data = rnorm (n = 12800 ,mean =0.0053,sd=0.0146),nrow=100,ncol=128,dimnames=list(c(1:100),c(1:128))); y-rnorm(n=100,mean=0.7958,sd=0.1900); The function is: test _lssvm (test ,test.ref,scale=F,type=regression,kernel=rbfdot,kpar=list(sigma=5)); The error message is: Error in if (n != dim(y)[1]) stop(Labels y and data x dont match) : argument is of length zero. This error message does not make sense to me. The R documentation for the lssvm function states that y can be a vector. The dimension of a vector is always NULL. Thus, the check function in the error message [if(n !=dim(y)[1]) stop] does not add up for me. Regards, Thomas On 14 May 2009, at 15:33, Max Kuhn wrote: To make things easier (using only two optimization parameters and not loosing performance) I wanted to use LS SVM regression (lssvm{kernlab}). But it looks to me that it is not yet implemented. At least I got error messages, which I could not find a solution for (Error in if (n ! _dim(y)[1] stop (Labels y and data x dont match). I've used the lssvm function in kernlab without issue. You should follow the posting guide and provide a reproducible example so that there is a possibility of answering your question. Plus, what versions etc. Max [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Plot data from table with column and row names
Dear All Sorry for what appears a trivial matter - I'm new to R and am stumbling ahead. I have a table of numerical data (36 rows by 12 columns) such as below: GM1 GM2 GM3 GM4 GM5 ...etc GM12 Run1 1 2 1 2 3 ... Run2 2 1 3 2 1 ... ... Run36 2 1 1 1 1 I would like to plot simple line graphs of some of the runs or all 36 to compare together but I can't even get a plot to have the GM1-GM12 on the x-axis and the numerical y -axis with the scores (1 to 3). I think that using Plot(x) is not correct for this type of data. Help would be appreciated - I'm sure I'm missing something... Matt -- View this message in context: http://www.nabble.com/Plot-data-from-table-with-column-and-row-names-tp23632750p23632750.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Mixed Models
Hello, I've run a Proc Mixed function on a set of data in SAS. The data was a result of an experiment that measured % viability over time and I wanted to compare a Large sample lets say 50L to a small sample say 5L. And compare the % viability between the 2 sizes to see if I get the same answer there are 8 samples of each size and the same 8 samples are tested every day over 10 days (day 0 - day 10). Now, Given that the same bottles are repeatedly tested each day then doing an ANOVA without taking account of the repeated measures nature of your experiment could lead to erroneous conclusions. The problem is that when I test a bottle 11 times over so many days each recorded value from that bottle cannot be considered statistically independent from the others. E.g. bottle A, day 0 the percentage recorded is high then it is more likely to be quite high on day 2 than to be quite low hence the two measures are not statistically independent.There are ANOVA models that can take account of repeated measures I have used the SAS procedure Proc Mixed for this. And I have produced a significant P-Value for size and not for time so I've shown there is an effect of time but not for size. I have also produced confidence intervals for each day over time how can I output the data in SAS to be read into R then plot a graph of the confidence intervals??Also is there a way of doing this whole analysis in R?Kind Regards,Al [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Least-square support vector machines regression!
Thomas, thanks for your valuable comment. I assume that you used the function for regression - not classification. I have been using it for classification and that is the issue. Looking at ?lssvm, it has regression is currently not supported in the details for the type argument. Max __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Where to find a changelog for the survival package
since some days I try to use the versions 2.35-4 of the survival package instead of versions 2.31, I had installed until now. Several changes in print.survfit, plot.survfit and seemingly in the structure of ratetabels effect some of my syntax files. Is there somewhere a documentation of these changes, besides the code itself? It's in the repository on R-Forge. The latest version is here: http://r-forge.r-project.org/plugins/scmsvn/viewcvs.php/pkg/survival/Changelog.09?rev=11234root=survivalview=markup Regards, Richie. Mathematical Sciences Unit HSL ATTENTION: This message contains privileged and confidential inform...{{dropped:20}} __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] efficiency when processing ordered data frames
Hoping for a little insight into how to make sure I have R running as efficiently as possible. Suppose I have a data frame, A, with n rows and m columns, where col1 is a date time stamp. Also suppose that when this data is imported (from a csv or SQL), that the data is already sorted such that the time stamp in col1 is in ascending (or descending) order. If I then wanted to select only the rows of A where col1 = a certain time, I am wondering if R has to read through the entirety of col1 to select those rows (all n of them). Is it possible for R to recognize (or somehow be told) that these rows are already in order, thus allowing the computation could be completed in ~log(n) row reads instead? Thanks! __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] How to google for R stuff?
Hi! I'm new to R programming, though I've been programming in other languages for years. One thing I find most frustrating about R is how difficult it is to use Google (or any other search tool) to look for answers to my R-related questions. With languages with even slightly more distinctive names like Perl, Java, Python, Matlab, OCaml, etc., usually including the name of the language in the query is enough to ensure that the top hits are relevant. But this trick does not work for R, because the letter R appears by itself in so many pages, that the chaff overwhelms the wheat, so to speak. So I'm curious to learn what strategies R users have found to get around this annoyance. TIA! KJ [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Plot data from table with column and row names
Here are a few possibilities: Lines - GM1 GM2 GM3 GM4 GM5 Run1 1 2 1 2 3 Run2 2 1 3 2 1 Run3 2 1 1 1 1 DF - read.table(textConnection(Lines), header = TRUE) long - as.data.frame.table(as.matrix(DF)) head(long) with(long, balloonplot(Var1, Var2, Freq)) library(lattice) dotplot(Freq ~ Var1, long, group = Var2, type = l) On Wed, May 20, 2009 at 6:21 AM, Matt Bishop m.bis...@ed.ac.uk wrote: Dear All Sorry for what appears a trivial matter - I'm new to R and am stumbling ahead. I have a table of numerical data (36 rows by 12 columns) such as below: GM1 GM2 GM3 GM4 GM5 ...etc GM12 Run1 1 2 1 2 3 ... Run2 2 1 3 2 1 ... ... Run36 2 1 1 1 1 I would like to plot simple line graphs of some of the runs or all 36 to compare together but I can't even get a plot to have the GM1-GM12 on the x-axis and the numerical y -axis with the scores (1 to 3). I think that using Plot(x) is not correct for this type of data. Help would be appreciated - I'm sure I'm missing something... Matt -- View this message in context: http://www.nabble.com/Plot-data-from-table-with-column-and-row-names-tp23632750p23632750.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Functions returning functions
On Wed, May 20, 2009 at 7:21 AM, Paulo Grahl pgr...@gmail.com wrote: A - function(parameters) { # calculations w/ parameters returning 'y' tmpf - function(x) { # function of 'y' } return(tmpf) } The value of the parameters are stored in an environment local to the function. Then I call x- something B-A(x) When R executes this last statement, does it perform all the calculations inside function A again (i.e., all the calculations that yield 'y') or the value of 'y' is already stored in the function's local environment ? A - function(q) { print(calculating y) y - q+1 function(x) print(paste(value of x:,x,value of y:,y)) } A(5) [1] calculating y function(x) print(paste(value of x:,x,value of y:,y)) environment: 0x07abe2a8 A(5)(4) [1] calculating y [1] value of x: 4 value of y: 6 A5 - A(5) [1] calculating y A5(4) [1] value of x: 4 value of y: 6 [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Too large a data set to be handled by R?
On Tue, May 19, 2009 at 11:59 PM, tsunhin wong thjw...@gmail.com wrote: In order to save time, I am planning to generate a data set of size 1500 x 2 with each data point a 9-digit decimal number, in order to save my time. I know R is limited to 2^31-1 and that my data set is not going to exceed this limit. But my laptop only has 2 Gb and is running 32-bit Windows / XP or Vista. 32-bit R on Windows XP with 2GB RAM has no problem with a matrix this size (not just integers, but also numerics): system.time(mm - matrix( numeric(1500 * 2), 1500, 2)) user system elapsed 0.590.231.87 system.time(nn - matrix( runif(1500 * 2), 1500, 2)) user system elapsed 2.660.64 13.39 system.time(oo - nn + 3) user system elapsed 0.240.170.41 system.time(pp - oo - oo) user system elapsed 0.150.130.28 [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to google for R stuff?
See http://finzi.psych.upenn.edu/ for many options for searching for R stuff. If you type R into Google, the R home page usually comes up first. I was amazed when this happened 9 years ago. And now, if I type R lmer into Google (without the quotes), a whole bunch of relevant stuff comes up, although it isn't so systematically arranged as with the other search options. Jon On 05/20/09 09:02, Kynn Jones wrote: Hi! I'm new to R programming, though I've been programming in other languages for years. One thing I find most frustrating about R is how difficult it is to use Google (or any other search tool) to look for answers to my R-related questions. With languages with even slightly more distinctive names like Perl, Java, Python, Matlab, OCaml, etc., usually including the name of the language in the query is enough to ensure that the top hits are relevant. But this trick does not work for R, because the letter R appears by itself in so many pages, that the chaff overwhelms the wheat, so to speak. So I'm curious to learn what strategies R users have found to get around this annoyance. TIA! KJ [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page: http://www.sas.upenn.edu/~baron Editor: Judgment and Decision Making (http://journal.sjdm.org) __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Error with regsubset in leaps package - vcov and all.best option (plus calculating VIFs for subsets)
Hi all I am hoping this is just a minor problem, I am trying to implement a best subsets regression procedure on some ecological datasets using the regsubsets function in the leaps package. The dataset contains 43 predictor variables plus the response (logcount) all in a dataframe called environment. I am implementing it as follows: library(leaps) subsets-regsubsets(logcount~.,data=environment,nvmax=10,nbest=2,really.big=FALSE,method=exhaustive) ###the subset regression runs fine when i run it as above and i can get all the usual summaries ###The problem comes when i try and get it to output the variance convariance matric by adding the option vcov=TRUE ##When I do that i get the following: subsets-regsubsets(logcount~.,data=environment,nvmax=10,nbest=2,really.big=FALSE,method=exhaustive,vcov=TRUE) Error in model.frame.default(data = environment, vcov = TRUE, formula = logcount~ : variable lengths differ (found for '(vcov)') traceback() 6: model.frame.default(data = environment, vcov = TRUE, formula = logcount~ .) 5: model.frame(data = environment, vcov = TRUE, formula = logcount~ .) 4: eval(expr, envir, enclos) 3: eval(mm, sys.frame(sys.parent())) 2: regsubsets.formula(logcount~ ., data = environment, nvmax = 10, really.big = TRUE, method = exhaustive, nbest = 5, vcov = TRUE) 1: regsubsets(obs ~ ., data = environment, nvmax = 10, really.big = TRUE, method = exhaustive, nbest = 5, vcov = TRUE) I get the same error when i try and add the all.best=TRUE option (as ideally i would like it to report the fits of all the subsets). All the predictor variables and the response are the same length (143) so not sure if I am misinterpreting the error or have misspecified the regsubsets? I was wanting to get the variance - covariance matrix as I believe I need it to calculate the Variance Inflation Factors (VIFs) for each of the models reported by regsubsets. As I want to exclude any models that exhibit multicollinerarity from later analysis, I am hoping to select say the 'best' 10 models and bootstrap them to find out more about how they perform. Or am I going about this all the wrong way? is there away to calulate vifs from regsubsets or pass it directly to something that calculates them e.g. VIF in the car package? Any help will be most appreciated, many thanks in advance Lara lara.har...@bbsrc.ac.uk __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to google for R stuff?
www.rseek.org is the best solution to this that I have found. Ian kynn wrote: Hi! I'm new to R programming, though I've been programming in other languages for years. One thing I find most frustrating about R is how difficult it is to use Google (or any other search tool) to look for answers to my R-related questions. With languages with even slightly more distinctive names like Perl, Java, Python, Matlab, OCaml, etc., usually including the name of the language in the query is enough to ensure that the top hits are relevant. But this trick does not work for R, because the letter R appears by itself in so many pages, that the chaff overwhelms the wheat, so to speak. So I'm curious to learn what strategies R users have found to get around this annoyance. TIA! KJ [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/How-to-google-for-R-stuff--tp23635068p23635296.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] efficiency when processing ordered data frames
How much is it currently costing you in time to do the selection process? Is it having a large impact on your program? Is it the part that is really consuming the overall time? What is your concern in this area? Here is the timing that it take so select from 10M values those that are less than a specific value. This takes less than 0.2 seconds: x - runif(1e7) system.time(y - x .5) user system elapsed 0.150.050.20 x - sort(x) system.time(y - x .5) user system elapsed 0.110.030.14 On Wed, May 20, 2009 at 8:54 AM, Brigid Mooney bkmoo...@gmail.com wrote: Hoping for a little insight into how to make sure I have R running as efficiently as possible. Suppose I have a data frame, A, with n rows and m columns, where col1 is a date time stamp. Also suppose that when this data is imported (from a csv or SQL), that the data is already sorted such that the time stamp in col1 is in ascending (or descending) order. If I then wanted to select only the rows of A where col1 = a certain time, I am wondering if R has to read through the entirety of col1 to select those rows (all n of them). Is it possible for R to recognize (or somehow be told) that these rows are already in order, thus allowing the computation could be completed in ~log(n) row reads instead? Thanks! __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.htmlhttp://www.r-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Jim Holtman Cincinnati, OH +1 513 646 9390 What is the problem that you are trying to solve? [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to google for R stuff?
One thing I find most frustrating about R is how difficult it is to use Google (or any other search tool) to look for answers to my R-related questions. With languages with even slightly more distinctive names like Perl, Java, Python, Matlab, OCaml, etc., usually including the name of the language in the query is enough to ensure that the top hits are relevant. But this trick does not work for R, because the letter R appears by itself in so many pages, that the chaff overwhelms the wheat, so to speak. There are loads of ways of finding information. Use the function RSiteSearch, or The R mail archive http://www.googlesyndicatedsearch.com/u/newcastlemaths RSeek http://www.rseek.org/ R Searchhttp://www.dangoldstein.com/search_r.html The R Graph Gallery http://addictedtor.free.fr/graphiques/ R Help Wiki http://wiki.r-project.org/rwiki/doku.php R manuals http://cran.r-project.org/manuals.html FAQshttp://cran.r-project.org/faqs.html Task Views http://cran.r-project.org/web/views/ News http://www.r-project.org/doc/Rnews/index.html Books http://www.r-project.org/doc/bib/R-books.html Cranberries http://dirk.eddelbuettel.com/cranberries/ R-Forge (http://r-forge.r-project.org/) and Bioconductor ( http://www.bioconductor.org/GettingStarted) also have their own search tools. Regards, Richie. Mathematical Sciences Unit HSL ATTENTION: This message contains privileged and confidential inform...{{dropped:20}} __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to google for R stuff?
Kynn Jones wrote: Hi! I'm new to R programming, though I've been programming in other languages for years. One thing I find most frustrating about R is how difficult it is to use Google (or any other search tool) to look for answers to my R-related questions. With languages with even slightly more distinctive names like Perl, Java, Python, Matlab, OCaml, etc., usually including the name of the language in the query is enough to ensure that the top hits are relevant. But this trick does not work for R, because the letter R appears by itself in so many pages, that the chaff overwhelms the wheat, so to speak. So I'm curious to learn what strategies R users have found to get around this annoyance. TIA! KJ [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Hi Kynn, I've had this problem too in the beginning. Luckily, my personal experience has taught me that almost all relevant R-related information can be found either by searching directly through the archives of the different R-forums or by using the functions RSiteSearch() or help.search(). The reference manuals provided with each package (easily accessible on CRAN) are also invaluable sources of information. Unfortunately, phrasing queries in a way that will yield relevant results is sometimes hard. Knowledge of the terminology mostly comes from experience, so patience is in order. Of course, as a last recourse, there's always the mailing list. Bottom line is, I suggest you try to avoid generic search engines and concentrate your efforts on the different R-forums (note that there are also package-specific forums). I suspect the more experienced R-users might have better strategies to propose though... Cheers, -- *Luc Villandré* /Biostatistician McGill University Health Center - Montreal Children's Hospital Research Institute/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] SEM:Standard error of std.coef estimates?
Dear Bastiaan, The standard errors of the standardized coefficients aren't simple because the standard deviations used to standardize the coefficients are also subject to sampling error. I can think of two ways to get standard errors for the standardized coefficients: by the delta method and by bootstrapping. Neither method is implemented in the sem package. Figuring out how to apply the former would require some work; I'll put it on my to-do list, but may not get to it. The second approach could easily be implemented via the boot package. I hope this helps, John -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of BdeGroot Sent: May-20-09 7:41 AM To: r-help@r-project.org Subject: [R] SEM:Standard error of std.coef estimates? Hi, I am currently working with the sem package in R, to create pathway diagrams. Id like to use the standardized path coeffcients. To get these, I use std.coef. However, using this yields only the standardized coefficients, but does not give me the standard error. Does someone know how to get std.coef to show the standard error of the standardized path coefficients as well? Thanks, Bastiaan PS: When I use std.coef, all I get is this: std.coef(path.model.SSI4) Std. Estimate par1 par1 0.39499 com_veg --- tempm par2 par2 0.35231 SNutBili --- tempm par3 par3 -0.68170 S_SSI4 --- tempm par4 par4 -0.39145 com_veg --- Wdeficit par5 par5 -0.60025 SNutBili --- Wdeficit par6 par6 -0.20562 S_SSI4 --- Wdeficit par7 par7 0.14871 SNutBili --- com_veg par8 par8 0.14905 S_SSI4 --- com_veg par9 par9 -0.39164 S_SSI4 --- SNutBili -- View this message in context: http://www.nabble.com/SEM%3AStandard-error-of- std.coef-estimates--tp23633227p23633227.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Trouble installing package 'systemfit'
I tried unnder R 2.9.0 and R 2.8.1. Both versions failed to install 'systemfit'. I downloaded file 'systemfit_1[1].0-8.zip' to install the package. I am using Windows 2000 service pack 4. The error message is: Error in gzfile(file, r) : cannot open the connection In addition: Warning message: In gzfile(file, r) : cannot open compressed file 'systemfit_1[1].0-8/DESCRIPTION', probable reason 'No such file or directory' Thanks! [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Getting lm() to work with a matrix
MikSmith wrote: Hi I'm fairly new to R and am trying to analyse some large spectral datasets using stepwise regression (fairly standard in this area). I have a field sampled dataset, of which a proportion has been held back for validation. I gather than step() needs to be fed a regression model and lm() can produce a multiple regression. I had thought something like: spectra.lm - lm(response[,3]~spectra.spec[,2:20]) might work but lm() doesnt appear to like being fed a range of columns. I suspect Ive missed something fairly fundamental here. Any help much appreciated best wishes mike Hi Mike, Indeed, functions like /lm()/ require the object fed to the /data/ argument to be either a list, a data frame or an environment containing the variables in the model. The /formula/ argument will then refer to column names or element names. In your situation, I suggest you typecast your matrix into a data frame using /as.data.frame()/. You can attribute column names by using /colnames()/. If you have a very large number of columns and you don't feel like giving them names individually, using the /paste()/ function should save you a lot of time. Also, character-type objects can be typecasted using /as.formula()/ to formula-like objects. So, using a combination of /paste()/ and /as.formula()/ might make your life a lot easier. HTH, -- *Luc Villandré* /Biostatistician McGill University Health Center - Montreal Children's Hospital Research Institute/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to google for R stuff?
For Google searches, I find that throwing in the term cran on every search helps weed out irrelevant pages. For example, instead of r residuals I type r cran residuals --Chris Ryan Original message Date: Wed, 20 May 2009 09:43:14 -0400 From: Luc Villandre villa...@dms.umontreal.ca Subject: Re: [R] How to google for R stuff? To: Kynn Jones kyn...@gmail.com Cc: r-help@r-project.org Kynn Jones wrote: Hi! I'm new to R programming, though I've been programming in other languages for years. One thing I find most frustrating about R is how difficult it is to use Google (or any other search tool) to look for answers to my R-related questions. With languages with even slightly more distinctive names like Perl, Java, Python, Matlab, OCaml, etc., usually including the name of the language in the query is enough to ensure that the top hits are relevant. But this trick does not work for R, because the letter R appears by itself in so many pages, that the chaff overwhelms the wheat, so to speak. So I'm curious to learn what strategies R users have found to get around this annoyance. TIA! KJ [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Hi Kynn, I've had this problem too in the beginning. Luckily, my personal experience has taught me that almost all relevant R-related information can be found either by searching directly through the archives of the different R-forums or by using the functions RSiteSearch() or help.search(). The reference manuals provided with each package (easily accessible on CRAN) are also invaluable sources of information. Unfortunately, phrasing queries in a way that will yield relevant results is sometimes hard. Knowledge of the terminology mostly comes from experience, so patience is in order. Of course, as a last recourse, there's always the mailing list. Bottom line is, I suggest you try to avoid generic search engines and concentrate your efforts on the different R-forums (note that there are also package-specific forums). I suspect the more experienced R-users might have better strategies to propose though... Cheers, -- *Luc Villandré* /Biostatistician McGill University Health Center - Montreal Children's Hospital Research Institute/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Trouble installing package 'systemfit'
Have you tried another mirror? It seems that downloaded file is incomplete. 2009/5/20 Rui Wang r...@hawaii.edu: I tried unnder R 2.9.0 and R 2.8.1. Both versions failed to install 'systemfit'. I downloaded file 'systemfit_1[1].0-8.zip' to install the package. I am using Windows 2000 service pack 4. The error message is: Error in gzfile(file, r) : cannot open the connection In addition: Warning message: In gzfile(file, r) : cannot open compressed file 'systemfit_1[1].0-8/DESCRIPTION', probable reason 'No such file or directory' Thanks! [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- HUANG Ronggui, Wincent PhD Candidate Dept of Public and Social Administration City University of Hong Kong Home page: http://asrr.r-forge.r-project.org/rghuang.html __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Trouble installing package 'systemfit'
Rui Wang wrote: I tried unnder R 2.9.0 and R 2.8.1. Both versions failed to install 'systemfit'. I downloaded file 'systemfit_1[1].0-8.zip' to install the package. I am using Windows 2000 service pack 4. The filename lost its canonical form, pelase try to rename it to: systemfit_1.0-8.zip Uwe Ligges The error message is: Error in gzfile(file, r) : cannot open the connection In addition: Warning message: In gzfile(file, r) : cannot open compressed file 'systemfit_1[1].0-8/DESCRIPTION', probable reason 'No such file or directory' Thanks! [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Error with regsubset in leaps package - vcov and all.best option (plus calculating VIFs for subsets)
On Wed, 20 May 2009, lara harrup (IAH-P) wrote: Hi all I am hoping this is just a minor problem, I am trying to implement a best subsets regression procedure on some ecological datasets using the regsubsets function in the leaps package. The dataset contains 43 predictor variables plus the response (logcount) all in a dataframe called environment. I am implementing it as follows: library(leaps) subsets-regsubsets(logcount~.,data=environment,nvmax=10,nbest=2,really.big=FALSE,method=exhaustive) ###the subset regression runs fine when i run it as above and i can get all the usual summaries ###The problem comes when i try and get it to output the variance convariance matric by adding the option vcov=TRUE Yes, that would be because there is no option vcov=TRUE for regsubsets. There is a vcov= option for the coef() method, which may be what is confusing you. snip I was wanting to get the variance - covariance matrix as I believe I need it to calculate the Variance Inflation Factors (VIFs) for each of the models reported by regsubsets. As I want to exclude any models that exhibit multicollinerarity from later analysis, I am hoping to select say the 'best' 10 models and bootstrap them to find out more about how they perform. As in the example on the help page, once you have run regsubsets() you can use coef() and vcov() on the object it returns to get coefficient estimates and variance-covariance matrices for any of the best models. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Random effects aov
Dear All I have a repeated measures design in which abundance was measured repeatedly over 10 months in three treatments (Tortoise A; Tortoise B and control) established in 6 blocks, i.e. crossed fixed effects. My original design incorporated two tortoises per treatment, however as fieldwork goes I ended up losing some animals. Rather than lose a couple of enclosures in the analysis and have to do a lmer, I thought I could include tortoise weight as an explanatory variable. For my treatments, tortoise weight in the control always = 0, while in general Tortoise A is twice as large as Tortoise B except when I lost animals. Is this the correct model? aov(Tel.ab~Tort.W+Treatment*Month+Error(Month/Block)) Or should tortoise weight be nested in Treatment, i.e not included as a fixed factor but including the fact that tortoises species may have an effect? I am utterly confused now as to whether that should be the case as to some extent Tort.W and Treatment are correlated. Any help would be much appreciated. Many thanks Christine -- Christine Griffiths School of Biological Sciences University of Bristol Woodland Road Bristol BS8 1UG Tel: 0117 9287593 Fax 0117 925 7374 christine.griffi...@bristol.ac.uk http://www.bio.bris.ac.uk/research/mammal/tortoises.html __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] function returning the name of an object
Hello R users, I'm trying to solve an apparently simple problem. I include a matrix in a model formula, and I want then to extract the related coefficients. Basically, I want a function func such that: mymatrix - cbind(rnorm(10),rnorm(10)) y - b - rnorm(10) model - lm(y ~ b + mymatrix) func(mymatrix,model) which returns only the 3rd and 4th coefficients. I thought to search by: grep(mymatrix,names(coef(model))) but I don't know how to extract the name mymatrix from the object mymatrix. Is there a specific function, something like func(mymatrix) returning the string mymatrix? Thanks so much for your time. Antonio Gasparrini Public and Environmental Health Research Unit (PEHRU) London School of Hygiene Tropical Medicine Keppel Street, London WC1E 7HT, UK Office: 0044 (0)20 79272406 - Mobile: 0044 (0)79 64925523 Skype contact: a.gasparrini http://www.lshtm.ac.uk/people/gasparrini.antonio ( http://www.lshtm.ac.uk/pehru/ ) [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Getting lm() to work with a matrix
G'day Luc, On Wed, 20 May 2009 09:58:41 -0400 Luc Villandre villa...@dms.umontreal.ca wrote: MikSmith wrote: [...] Indeed, functions like /lm()/ require the object fed to the /data/ argument to be either [...] But the data argument is optional and does not need to be specified. In your situation, I suggest you typecast your matrix into a data frame using /as.data.frame()/. [...] My guess is that he is already working with a data frame and does not work with matrices, otherwise he should not have encountered problems: R response - matrix(rnorm(120), ncol=4) R spectra.spec - matrix(rnorm(900), ncol=30) R spectra.lm - lm(response[,3]~spectra.spec[,2:20]) R spectra.lm Call: lm(formula = response[, 3] ~ spectra.spec[, 2:20]) Coefficients: (Intercept) spectra.spec[, 2:20]1 -0.48404 0.42503 spectra.spec[, 2:20]2 spectra.spec[, 2:20]3 -0.08955-0.27605 spectra.spec[, 2:20]4 spectra.spec[, 2:20]5 -0.16832-0.14107 spectra.spec[, 2:20]6 spectra.spec[, 2:20]7 -0.47009-0.23672 spectra.spec[, 2:20]8 spectra.spec[, 2:20]9 0.12920 0.23306 spectra.spec[, 2:20]10 spectra.spec[, 2:20]11 -0.28586 0.03579 spectra.spec[, 2:20]12 spectra.spec[, 2:20]13 0.10676-0.34407 spectra.spec[, 2:20]14 spectra.spec[, 2:20]15 0.20253-0.17259 spectra.spec[, 2:20]16 spectra.spec[, 2:20]17 0.19765 0.40705 spectra.spec[, 2:20]18 spectra.spec[, 2:20]19 -0.12448-0.17149 Cheers, Berwin __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Trouble installing package 'systemfit'
Renaming the file worked! Thanks! - Original Message - From: Uwe Ligges lig...@statistik.tu-dortmund.de Date: Wednesday, May 20, 2009 10:07 am Subject: Re: [R] Trouble installing package 'systemfit' To: Rui Wang r...@hawaii.edu Cc: r-help@r-project.org Rui Wang wrote: I tried unnder R 2.9.0 and R 2.8.1. Both versions failed to install 'systemfit'. I downloaded file 'systemfit_1[1].0-8.zip' to install the package. I am using Windows 2000 service pack 4. The filename lost its canonical form, pelase try to rename it to: systemfit_1.0-8.zip Uwe Ligges The error message is: Error in gzfile(file, r) : cannot open the connection In addition: Warning message: In gzfile(file, r) : cannot open compressed file 'systemfit_1[1].0- 8/DESCRIPTION', probable reason 'No such file or directory' Thanks! [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R- project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] problem with APPLY
Hello, The apply function seems to behave oddly with my code below NB : H1 is a data frame. (data in the attached file.) # the first lines are: 1 02/01/2008 0.00 0 0 0.00 0 2 03/01/2008 0.00 0 0 0.00 0 3 04/01/2008 0.00 0 0 0.00 0 4 07/01/2008 0.00 0 0 0.00 0 5 08/01/2008 0.00 0 0 0.00 0 6 09/01/2008 0.00 0 0 0.00 0 7 10/01/2008 0.00 0 0 0.00 0 8 11/01/2008 1.010391 0 0 1.102169 0 ... The aim of the code is to extract those lines for which there is a strictly positive value in the second column AND in one of the others: reper=function(x){as.numeric(x[2]1 any(x[3:length(x)]1))} TAB1= H1[which(apply(H1,1,reper)0),] Strangely, this is OK for all the lines, except for the last one. In fact, in H1, the last 2 lines are: 258 29/12/2008 1.476535 1.187615 0 0.00 0 259 30/12/2008 0.00 1.147888 0 0.00 0 Obviously, line 258 should be the last line of TAB1, but it is not the case (it does not appear at all) and I really don't understand why. This is all the more strange since applying the function reper only to this line 258 gives a 1 as expected... Can someone help ? Thanks, Henri do[, 1] V3 V5 V7 V13 V31 1 02/01/2008 0 0 0 0 0 2 03/01/2008 0 0 0 0 0 3 04/01/2008 0 0 0 0 0 4 07/01/2008 0 0 0 0 0 5 08/01/2008 0 0 0 0 0 6 09/01/2008 0 0 0 0 0 7 10/01/2008 0 0 0 0 0 8 11/01/2008 1.01039075593190 0 0 1.10216867469880 0 9 14/01/2008 0 0 0 0 0 10 15/01/2008 0 0 0 0 0 11 16/01/2008 0 0 0 0 0 12 17/01/2008 0 0 0 0 0 13 18/01/2008 0 0 0 0 0 14 21/01/2008 0 1.91598986420635 0 0 0 15 22/01/2008 0 0 0 1.67943418163028 0 16 23/01/2008 0 1.72752274788613 0 0 0 17 24/01/2008 0 0 0 0 0 18 25/01/2008 0 0 0 0 0 19 28/01/2008 0 1.58121398689715 0 0 0 20 29/01/2008 0 0 0 0 0 21 30/01/2008 0 0 0 0 0 22 31/01/2008 0 0 0 0 0 23 01/02/2008 0 0 0 0 0 24 04/02/2008 0 0 0 0 0 25 05/02/2008 0 0 0 0 0 26 06/02/2008 0 0 0 0 0 27 07/02/2008 0 0 0 0 0 28 08/02/2008 2.14000732355798 1.69766978689504 0 1.75685318945262 0 29 11/02/2008 0 0 0 0 0 30 12/02/2008 0 0 0 0 0 31 13/02/2008 0 0 0 0 0 32 14/02/2008 1.46825855993268 1.01452104942038 0 1.36151226158038 0 33 15/02/2008 0 0 0 0 0 34 18/02/2008 1.23828782287823 1.85457398206402 0 1.01737020551797 0 35 19/02/2008 0 0 0 0 0 36 20/02/2008 0 0 0 1.16595050312755 0 37 21/02/2008 0 0 0 0 0 38 22/02/2008 0 0 0 0 0 39 25/02/2008 0 0 0 0 0 40 26/02/2008 0 0 0 0 0 41 27/02/2008 0 0 0 1.14892847454562 0 42 28/02/2008 0 0 0 0 0 43 29/02/2008 0 0 0 1.08156034746327 0 44 03/03/2008 0 0 0 0 0 45 04/03/2008 0 0 0 0 0 46 05/03/2008 0 0 0 0 0 47 06/03/2008 0 0 0 0 0 48 07/03/2008 0 0 0 0 0 49 10/03/2008 0 0 0 0 0 50 11/03/2008 0 0 0 0 0 51 12/03/2008 0 0 0 0 0 52 13/03/2008 0 0 0 0 0 53 14/03/2008 0 0 0 0 0 54 17/03/2008 4.35512801471512 5.36991654793405 0 6.16519844357977 0 55 18/03/2008 2.79350502621745 2.11529748269272 0 3.52300391995049 0 56 19/03/2008 2.71891047108730 2.44490502825019 0 2.88516037009928 0 57 20/03/2008 0 0 0 0 0 58 21/03/2008 0 0 0 0 0 59 24/03/2008 5.54031680331131 5.79959578768216 0 6.7272138683414 0 60 25/03/2008 0 0 0 0 0 61 26/03/2008 0 0 0 0 0 62 27/03/2008 0 0 0 0 0 63 28/03/2008 0 0 0 0 0 64 31/03/2008 1.36298613237674 1.93688809995221 0 1.62820120724346 0 65 01/04/2008 0 0 0 0 0 66 02/04/2008 0 1.50365203568443 0 1.41661422278162 0 67 03/04/2008 0 0 0 0 0 68 04/04/2008 0 0 0 0 0 69 07/04/2008 0 0 0 0 0 70 08/04/2008 0 0 0 0 0 71 09/04/2008 0 0 0 0 0 72 10/04/2008 0 0 0 0 0 73 11/04/2008 0 0 0 0 0 74 14/04/2008 0 0 0 0 0 75 15/04/2008 0 1.12993898169451 0 0 0 76 16/04/2008 0 1.64919239565466 0 0 0 77 17/04/2008 1.85794201323402 2.32701547844896 0 2.13671788020485 0 78 18/04/2008 0 0 0 0 0 79 21/04/2008 0 0 0 0 0 80 22/04/2008 0 0 0 0 0 81 23/04/2008 0 0 0 0 0 82 24/04/2008 0 0 0 0 0 83 25/04/2008 0 0 0 0 0 84 28/04/2008 0 0 0 0 0 85 29/04/2008 1.41455686561253 1.23468581006293 0 1.41084889962815 0 86 30/04/2008 0 0 0 0 0 87 01/05/2008 0 1.5699823478825 0 0 0 88 02/05/2008 0 0 0 0 0 89 05/05/2008 0 0 0 0 0 90 06/05/2008 0 0 0 0 0 91 07/05/2008 0 0 0 0 0 92 08/05/2008 0 0 0 0 0 93 09/05/2008 0 0 0 0 0 94 12/05/2008 0 0 0 0 0 95 13/05/2008 0 0 0 0 0 96 14/05/2008 0 0 0 0 0 97 15/05/2008 0 0 0 0 0 98 16/05/2008 0 0 0 0 0 99 19/05/2008 0 0 0 0 0 100 20/05/2008 0 0 0 0 0 101 21/05/2008 0 0 0 0 0 102 22/05/2008 0 0 0 0 0 103 23/05/2008 0 0 0 0 0 104 26/05/2008 0 0 0 0 0 105 27/05/2008 0 0 0 0 0 106 28/05/2008 0 0 0 0 0 107 29/05/2008 0 0 0 0 0 108 30/05/2008 0 0 0 0 0 109 02/06/2008 0 0 0 0 0 110 03/06/2008 0 0 0 0 0 111 04/06/2008 0 0 0 0 0 112 05/06/2008 0 0 0 0 0 113 06/06/2008 0 0 0 0 0 114 09/06/2008 0 0 0 0 0 115 10/06/2008 0 0 0 0 0 116 11/06/2008 0 0 0 0 0 117 12/06/2008 0 0 0 0 0 118 13/06/2008 0 0 0 0 0 119 16/06/2008 0 0 0 0 0 120 17/06/2008 0 0 0 0 0 121 18/06/2008 0 0 0 0 0 122 19/06/2008 0 0 0 0 0 123 20/06/2008 0 0 0 0 0 124 23/06/2008 0 0 0 0 0 125 24/06/2008 0 0 0 0 0 126 25/06/2008 0 0 0 0 0 127 26/06/2008 0 0 0 0 0 128 27/06/2008 0 0 0 0 0
Re: [R] How to google for R stuff?
There is also the relatively new RSiteSearch package. It's RSiteSearch.function searches only help pages of contributed packages but returns the result in a data.frame (of class RSiteSearch) sorted to put the most interesting package first with help pages sorted within packages. If this package is installed, system.file('doc', 'RSiteSearch.pdf', package='RSiteSearch') will give you the location of a 2-page description of the most important features of this package including examples that work. Since that document was written, we've added | and for combining the objects returned by different searches and packageSum2 to add information from installed packages not available from RSiteSearch itself. For example, I'm giving an invited presentation on Fitting Nonlinear Differential Equations to Data in R as part of a Dynamics Workshop in Vancouver this June 4-6 (http://stat.sfu.ca/~dac5/workshop09/Welcome.html). To prepare for that, I first did the following: de - RSiteSearch.function(differential equation) des - RSiteSearch.function(differential equations) # With de and des, each finds things missed by the other. de. - de | des # combine into one sumDE - packageSum2(de.) # add details on installed packages. This helped me decide which packages I should look at first. Hope this helps. Spencer Graves cr...@binghamton.edu wrote: For Google searches, I find that throwing in the term cran on every search helps weed out irrelevant pages. For example, instead of r residuals I type r cran residuals --Chris Ryan Original message Date: Wed, 20 May 2009 09:43:14 -0400 From: Luc Villandre villa...@dms.umontreal.ca Subject: Re: [R] How to google for R stuff? To: Kynn Jones kyn...@gmail.com Cc: r-help@r-project.org Kynn Jones wrote: Hi! I'm new to R programming, though I've been programming in other languages for years. One thing I find most frustrating about R is how difficult it is to use Google (or any other search tool) to look for answers to my R-related questions. With languages with even slightly more distinctive names like Perl, Java, Python, Matlab, OCaml, etc., usually including the name of the language in the query is enough to ensure that the top hits are relevant. But this trick does not work for R, because the letter R appears by itself in so many pages, that the chaff overwhelms the wheat, so to speak. So I'm curious to learn what strategies R users have found to get around this annoyance. TIA! KJ [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Hi Kynn, I've had this problem too in the beginning. Luckily, my personal experience has taught me that almost all relevant R-related information can be found either by searching directly through the archives of the different R-forums or by using the functions RSiteSearch() or help.search(). The reference manuals provided with each package (easily accessible on CRAN) are also invaluable sources of information. Unfortunately, phrasing queries in a way that will yield relevant results is sometimes hard. Knowledge of the terminology mostly comes from experience, so patience is in order. Of course, as a last recourse, there's always the mailing list. Bottom line is, I suggest you try to avoid generic search engines and concentrate your efforts on the different R-forums (note that there are also package-specific forums). I suspect the more experienced R-users might have better strategies to propose though... Cheers, -- *Luc Villandré* /Biostatistician McGill University Health Center - Montreal Children's Hospital Research Institute/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] SEM:Standard error of std.coef estimates?
Dear John, Thank you for your reply. I would like to try the bootstrapping method. I have the boot package, however, I have not used it before. I do not know how to compute the correct code to calculate the standarized errors. If possible and easily achievable, could you please tell me what to do specifically or provide some more specific guidelines? Thanks, Bastiaan John Fox-6 wrote: Dear Bastiaan, The standard errors of the standardized coefficients aren't simple because the standard deviations used to standardize the coefficients are also subject to sampling error. I can think of two ways to get standard errors for the standardized coefficients: by the delta method and by bootstrapping. Neither method is implemented in the sem package. Figuring out how to apply the former would require some work; I'll put it on my to-do list, but may not get to it. The second approach could easily be implemented via the boot package. I hope this helps, John -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of BdeGroot Sent: May-20-09 7:41 AM To: r-help@r-project.org Subject: [R] SEM:Standard error of std.coef estimates? Hi, I am currently working with the sem package in R, to create pathway diagrams. Id like to use the standardized path coeffcients. To get these, I use std.coef. However, using this yields only the standardized coefficients, but does not give me the standard error. Does someone know how to get std.coef to show the standard error of the standardized path coefficients as well? Thanks, Bastiaan PS: When I use std.coef, all I get is this: std.coef(path.model.SSI4) Std. Estimate par1 par1 0.39499 com_veg --- tempm par2 par2 0.35231 SNutBili --- tempm par3 par3 -0.68170 S_SSI4 --- tempm par4 par4 -0.39145 com_veg --- Wdeficit par5 par5 -0.60025 SNutBili --- Wdeficit par6 par6 -0.20562 S_SSI4 --- Wdeficit par7 par7 0.14871 SNutBili --- com_veg par8 par8 0.14905 S_SSI4 --- com_veg par9 par9 -0.39164 S_SSI4 --- SNutBili -- View this message in context: http://www.nabble.com/SEM%3AStandard-error-of- std.coef-estimates--tp23633227p23633227.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/SEM%3AStandard-error-of-std.coef-estimates--tp23633227p23636945.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Class for time of day?
What is the recommended class for time of day (independent of calendar date)? And what is the recommended way to get the time of day from a POSIXct object? (Not a string representation, but a computable representation.) I have looked in the man page for DateTimeClasses, in the Time Series Analysis Task View and in Spector's Data Manipulation book but haven't found these. Clearly I can create my own Time class and hack around with the internal representation of POSIXct, e.g. days - unclass(d)/(24*3600) days-floor(days) and write print.Time, `-.Time`, etc. etc. but I expect there is already a standard class or CRAN package. -s [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] meaning of order-vector in object of class hclust
I'm trying to export the dendrogram created in R such that I can rebuild it inside an other program. However, I don't fully understand the relation between the merge, height and order vectors. This is what I do grasp. The merge-matrix shows how the original observations were merged into a tree structure. The height-vector contains the heights for each of the nodes in the tree. The order of the merge-matrix and the height-vector is the same. This means that row *i* in the matrix corresponds to row *i* in the vector. Then there is the order-vector. The documentation describes it as follows: order a vector giving the permutation of the original observations suitable for plotting, in the sense that a cluster plot using this ordering and matrix merge will not have crossings of the branches. So far, I get it reorders the nodes to prevent overlapping branches, but I don't understand how the values in this vector correspond to the values in the other two structures. So what does row *i* in the order-vector say about the other structures? Should I reorder the merge-matrix and height-vector, according to the values in the order-vector, before constructing the tree? Hopefully someone can explain to me how this works. Thanks in advance for any help you can provide. Kind regards, Pieter [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] stationarity tests
How can I make sure the residual signal, after subtracting the trend extracted through some technique, is actually trend-free ? I would greatly appreciate any suggestion about some Stationarity tests. I'd like to make sure I have got the difference between ACF and PACF right. In the following I am citing some definitions. I would appreciate your thoughts. ACF(k) estimates the correlation between y(t) and y(t-k) like an ordinary correlation coefficient. ACF is the simple ( i.e. unconditional ) correlation between a time series and it's lags thus y(t)=a+b*y(t-k) gnerates the kth autocoreelation coefficient (b). If we have form y(t)=a+b*y(t-1)+c*y(t-2) .. then (c) is the PARTIAL AUTOCORRELATION COEFFFICIENT or in other words the CONDITIONAL CORRELATION of lag 2 given lag1 PACF(k) estimates the correlation between y(t) and y(t-k) adjusted for the effects of y(t-1), ..., y(t-k+1). Model identification is achieved by looking at the pattern of the ACF and PACF. - If the ACF dies off exponentially, but the PACF has p spikes, AR(p) is indicated. - If the ACF has q spikes and the PACF dies off exponentially, MA(q) is indicated. The ACF and the PACF for the resulting stationary series is used to determine the best B/J model for the series according to the following rules: a. If the ACF trails off and the PACF shows spikes, then an AR model with order p = number of significant PACF spikes is the best model. b. If the PACF trails off and the ACF shows spikes, then an MA model with order q= number of significant ACF spikes is the best model. c. If both the ACF and the PACF trail off then a ARMA model is used with p=1 and q=1. Thank you very much, Maura Thank you very much. Best regards, Maura Edelweiss tutti i telefonini TIM! [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to google for R stuff?
Kynn writes: So I'm curious to learn what strategies R users have found to get around this annoyance. I use Rseek for most of my R questions: http://www.rseek.org/ cur -- Curt Seeliger, Data Ranger Raytheon Information Services - Contractor to ORD seeliger.c...@epa.gov 541/754-4638 [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] arrangement of crowded labels
Look at the spread.labs and the dynIdentify and TkIdentify functions in the TeachingDemos package. -- Gregory (Greg) L. Snow Ph.D. Statistical Data Center Intermountain Healthcare greg.s...@imail.org 801.408.8111 -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r- project.org] On Behalf Of Thomas Zumbrunn Sent: Wednesday, May 20, 2009 12:18 AM To: r-help@r-project.org Subject: [R] arrangement of crowded labels Dear R users I'm looking for algorithms that assist in spreading out crowded labels, e.g. labels of points in a scatter plot, in order to obtain a nicer visual appearance and better legibility. I'm probably just stuck because I didn't find the right key words for a successful search on the R websites or in the mailing list archives. Any hints are appreciated. Thomas Zumbrunn University of Basel __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting- guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] drc results differ for different versions
On May 20, 2009, at 11:20 AM, Hans Vermeiren wrote: Hello, We use drc to fit dose-response curves, recently we discovered that there are quite different standard error values returned for the same dataset depending on the drc-version / R-version that was used (not clear which factor is important) On R 2.9.0 using drc_1.6-3 we get an IC50 of 1.27447 and a standard error on the IC50 of 0.43540 Whereas on R 2.7.0 using drc_1.4-2 the IC50 is 1.2039e+00 and the standard error is 3.7752e-03 Normally I would use the most recent version (both R and drc library) but it seems to me that a standard error of 0.4 on a mean of 1.2 is too big, so I trust the values we get with the older versions more Has anyone suggestions on - how to solve these discrepancies, if possible - how to calculate which one of the 2 solutions is the correct one? Thanks a lot, Hans Vermeiren Demo (on a windows machine, while the issue was actually discovered on our ubuntu linux server): 1) sessionInfo() R version 2.7.0 (2008-04-22) i386-pc-mingw32 locale: LC_COLLATE=Dutch_Belgium.1252;LC_CTYPE=Dutch_Belgium. 1252;LC_MONETARY=Du tch_Belgium.1252;LC_NUMERIC=C;LC_TIME=Dutch_Belgium.1252 attached base packages: [1] stats graphics grDevices utils datasets methods base other attached packages: [1] drc_1.4-2 plotrix_2.4-2 nlme_3.1-89MASS_7.2-41 lattice_0.17-6 [6] alr3_1.1.7 loaded via a namespace (and not attached): [1] grid_2.7.0 d-data.frame(dose=c(2.00e-05, 4.00e-06, 8.00e-07, 1.60e-07, 3.20e-08, 6.40e-09, 1.28e-09, 2.56e-10, 5.10e-11, 1.00e-11, 2.00e-05, 4.00e-06, 8.00e-07, 1.60e-07, 3.20e-08, 6.40e-09, 1.28e-09, 2.56e-10, 5.10e-11, 1.00e-11), response=c(97.202,81.670,47.292,16.924, 16.832, 6.832, 11.118, 1.319, 5.495, -3.352, 102.464, 83.114, 50.631, 22.792, 18.348, 19.066, 27.794, 14.682, 11.992, 12.868)) m- drm(response ~ (log10(dose*1e6)), data = d, fct = l4(fixed = c(NA,NA,NA,NA), names = c(hs, bottom, top, ec50)), logDose = 10, control = drmc(useD = T)) summary(m) results in: Model fitted: Log-logistic (ED50 as parameter) (4 parms) Parameter estimates: Estimate Std. Error t-value p-value hs:(Intercept) -9.8065e-01 2.5821e-03 -3.7979e+02 2.248e-33 bottom:(Intercept) 1.0955e+01 2.2546e-02 4.8591e+02 4.364e-35 top:(Intercept) 1.0502e+02 9.0935e-02 1.1549e+03 4.210e-41 ec50:(Intercept)1.2039e+00 3.7752e-03 3.1890e+02 3.681e-32 Residual standard error: 7.026655 (16 degrees of freedom) = = == === 2) sessionInfo() R version 2.9.0 (2009-04-17) i386-pc-mingw32 locale: LC_COLLATE=Dutch_Belgium.1252;LC_CTYPE=Dutch_Belgium. 1252;LC_MONETARY=Du tch_Belgium.1252;LC_NUMERIC=C;LC_TIME=Dutch_Belgium.1252 attached base packages: [1] stats graphics grDevices utils datasets methods base other attached packages: [1] drc_1.6-3 plotrix_2.5-5 nlme_3.1-90 MASS_7.2-46 magic_1.4-4 abind_1.1-0 lattice_0.17-22 alr3_1.1.7 loaded via a namespace (and not attached): [1] grid_2.9.0 tools_2.9.0 d-data.frame(dose=c(2.00e-05, 4.00e-06, 8.00e-07, 1.60e-07, 3.20e-08, 6.40e-09, 1.28e-09, 2.56e-10, 5.10e-11, 1.00e-11, 2.00e-05, 4.00e-06, 8.00e-07, 1.60e-07, 3.20e-08, 6.40e-09, 1.28e-09, 2.56e-10, 5.10e-11, 1.00e-11), response=c(97.202,81.670,47.292,16.924, 16.832, 6.832, 11.118, 1.319, 5.495, -3.352, 102.464, 83.114, 50.631, 22.792, 18.348, 19.066, 27.794, 14.682, 11.992, 12.868)) m- drm(response ~ (log10(dose*1e6)), data = d, fct = l4(fixed = c(NA,NA,NA,NA), names = c(hs, bottom, top, ec50)), logDose = 10, control = drmc(useD = T)) summary(m) gives: Model fitted: Log-logistic (ED50 as parameter) (4 parms) Parameter estimates: Estimate Std. Error t-value p-value hs:(Intercept) -0.952660.25778 -3.695640.0020 bottom:(Intercept) 10.974372.24421 4.890090.0002 top:(Intercept)106.383739.98378 10.65565 1.127e-08 ec50:(Intercept) 1.274470.43540 2.927120.0099 Residual standard error: 7.020175 (16 degrees of freedom) Hans, You have three important factors changing here. The version of R, the version of drc and the versions of any relevant drc dependencies (alr3, lattice, magic, MASS, nlme, plotrix). I would first try to install the newer version of drc on the older R system (all else staying the same) and see what you get. Don't run update.packages() here, lest you change other things. Just install the newer version of drc. If you get the same results as the older version, then it might lead you to something in R or one of the package dependencies changing. If you get a different result, then it would lead to something in drc changing. You can also install the old version of drc on your more recent R system to see what you get, which might help to confirm behavior. The old source version of drc would be
Re: [R] How to google for R stuff?
Dear Dieter: Thanks for the correction. I failed to test the code as written before I posted it. Spencer Graves Dieter Menne wrote: spencerg spencer.graves at prodsyse.com writes: de - RSiteSearch.function(differential equation) des - RSiteSearch.function(differential equations) # With de and des, each finds things missed by the other. de. - de | des # combine into one sumDE - packageSum2(de.) # add details on installed packages. Should be PackageSum2(de.) Dieter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] evaluating partitions in CLUE
Hello, I'm starting to use CLUE to compare clusterings. I have some cluster structures obtained outside R, which are simlply vectors of lenght N (N: number of objects), which contain a number indicating the cluster to which each object belongs. I report below a portion of one of these: V1 1 12 2 1 3 2 4 6 5 15 6 9 7 5 8 8 9 12 10 9 11 10 12 2 13 7 14 12 15 10 - which indicates that object 1 is in cluster 12, object 2 is in cluster 1 etc. Is there a way to evaluate the dissimilarity of clusterings of this sort without transforming them into ensembles or, alternatively, is there a way to turn these vectors into ensembles Thanks a lot! Mario -- Andrea Mario Lavezzi Dipartimento Studi su Politica, Diritto e Società Piazza Bologni 8 90134 Palermo, Italy tel. ++39 091 6625650 fax ++39 091 6112023 skype: lavezzimario email: lave...@unipa.it web: http://www.unipa.it/~lavezzi [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] drc results differ for different versions
Hello, We use drc to fit dose-response curves, recently we discovered that there are quite different standard error values returned for the same dataset depending on the drc-version / R-version that was used (not clear which factor is important) On R 2.9.0 using drc_1.6-3 we get an IC50 of 1.27447 and a standard error on the IC50 of 0.43540 Whereas on R 2.7.0 using drc_1.4-2 the IC50 is 1.2039e+00 and the standard error is 3.7752e-03 Normally I would use the most recent version (both R and drc library) but it seems to me that a standard error of 0.4 on a mean of 1.2 is too big, so I trust the values we get with the older versions more Has anyone suggestions on - how to solve these discrepancies, if possible - how to calculate which one of the 2 solutions is the correct one? Thanks a lot, Hans Vermeiren Demo (on a windows machine, while the issue was actually discovered on our ubuntu linux server): 1) sessionInfo() R version 2.7.0 (2008-04-22) i386-pc-mingw32 locale: LC_COLLATE=Dutch_Belgium.1252;LC_CTYPE=Dutch_Belgium.1252;LC_MONETARY=Du tch_Belgium.1252;LC_NUMERIC=C;LC_TIME=Dutch_Belgium.1252 attached base packages: [1] stats graphics grDevices utils datasets methods base other attached packages: [1] drc_1.4-2 plotrix_2.4-2 nlme_3.1-89MASS_7.2-41 lattice_0.17-6 [6] alr3_1.1.7 loaded via a namespace (and not attached): [1] grid_2.7.0 d-data.frame(dose=c(2.00e-05, 4.00e-06, 8.00e-07, 1.60e-07, 3.20e-08, 6.40e-09, 1.28e-09, 2.56e-10, 5.10e-11, 1.00e-11, 2.00e-05, 4.00e-06, 8.00e-07, 1.60e-07, 3.20e-08, 6.40e-09, 1.28e-09, 2.56e-10, 5.10e-11, 1.00e-11), response=c(97.202,81.670,47.292,16.924, 16.832, 6.832, 11.118, 1.319, 5.495, -3.352, 102.464, 83.114, 50.631, 22.792, 18.348, 19.066, 27.794, 14.682, 11.992, 12.868)) m- drm(response ~ (log10(dose*1e6)), data = d, fct = l4(fixed = c(NA,NA,NA,NA), names = c(hs, bottom, top, ec50)), logDose = 10, control = drmc(useD = T)) summary(m) results in: Model fitted: Log-logistic (ED50 as parameter) (4 parms) Parameter estimates: Estimate Std. Error t-value p-value hs:(Intercept) -9.8065e-01 2.5821e-03 -3.7979e+02 2.248e-33 bottom:(Intercept) 1.0955e+01 2.2546e-02 4.8591e+02 4.364e-35 top:(Intercept) 1.0502e+02 9.0935e-02 1.1549e+03 4.210e-41 ec50:(Intercept)1.2039e+00 3.7752e-03 3.1890e+02 3.681e-32 Residual standard error: 7.026655 (16 degrees of freedom) === 2) sessionInfo() R version 2.9.0 (2009-04-17) i386-pc-mingw32 locale: LC_COLLATE=Dutch_Belgium.1252;LC_CTYPE=Dutch_Belgium.1252;LC_MONETARY=Du tch_Belgium.1252;LC_NUMERIC=C;LC_TIME=Dutch_Belgium.1252 attached base packages: [1] stats graphics grDevices utils datasets methods base other attached packages: [1] drc_1.6-3 plotrix_2.5-5 nlme_3.1-90 MASS_7.2-46 magic_1.4-4 abind_1.1-0 lattice_0.17-22 alr3_1.1.7 loaded via a namespace (and not attached): [1] grid_2.9.0 tools_2.9.0 d-data.frame(dose=c(2.00e-05, 4.00e-06, 8.00e-07, 1.60e-07, 3.20e-08, 6.40e-09, 1.28e-09, 2.56e-10, 5.10e-11, 1.00e-11, 2.00e-05, 4.00e-06, 8.00e-07, 1.60e-07, 3.20e-08, 6.40e-09, 1.28e-09, 2.56e-10, 5.10e-11, 1.00e-11), response=c(97.202,81.670,47.292,16.924, 16.832, 6.832, 11.118, 1.319, 5.495, -3.352, 102.464, 83.114, 50.631, 22.792, 18.348, 19.066, 27.794, 14.682, 11.992, 12.868)) m- drm(response ~ (log10(dose*1e6)), data = d, fct = l4(fixed = c(NA,NA,NA,NA), names = c(hs, bottom, top, ec50)), logDose = 10, control = drmc(useD = T)) summary(m) gives: Model fitted: Log-logistic (ED50 as parameter) (4 parms) Parameter estimates: Estimate Std. Error t-value p-value hs:(Intercept) -0.952660.25778 -3.695640.0020 bottom:(Intercept) 10.974372.24421 4.890090.0002 top:(Intercept)106.383739.98378 10.65565 1.127e-08 ec50:(Intercept) 1.274470.43540 2.927120.0099 Residual standard error: 7.020175 (16 degrees of freedom) -- This e-mail and its attachment(s) (if any) may contain confidential and/or proprietary information and is intended for its addressee(s) only. Any unauthorized use of the information contained herein (including, but not limited to, alteration, reproduction, communication, distribution or any other form of dissemination) is strictly prohibited. If you are not the intended addressee, please notify the orginator promptly and delete this e-mail and its attachment(s) (if any) subsequently. Galapagos nor any of its affiliates shall be liable for direct, special, indirect or consequential damages arising from alteration of the contents of this message (by a third party) or as a result of a virus being passed on. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide
Re: [R] RGoogleDocs: can now see documents but cannot get content.
Hi Farrel This particular problem is a trivial issue of an argument out of place due to a change in the function definition during the development. There is a new version of the package (0.2-2) and it also uses a slightly different approach (and function) to pull the values into the form of an R data frame. Please try that and hopefully it will work. The code in the run.pdf (or run.html) file on the Web page and in the package works and is the best and shortest example of sheetAsMatrix(). Let me know if there are still problems. D. Farrel Buchinsky wrote: The author of the package, Duncan Temple Lang posted an update. I have installed it and now can list my spreadsheets but alas I cannot read the data within any of them. Has anybody been able to get it to work. I would love to see a real live example of sheetAsMatrix I am not sure how to specify sheet and con = sh...@connection. I have tried many ways but just get: Error in !includeEmpty : invalid argument type Windows Vista (with UAC disabled) R 2.9.0 Farrel Buchinsky [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] SEM:Standard error of std.coef estimates?
Dear Bastiaan, I've written an appendix on bootstrapping regression models, available at http://socserv.mcmaster.ca/jfox/Books/Companion/appendix-bootstrapping.pdf , which describes generally how to proceed. In outline, you'll write a function that takes your data matrix (not covariance matrix) as an argument, along with a vector argument for indexing the data matrix. Your function will calculate covariances from the indexed data matrix, fit your model to this covariance matrix, get the standardized coefficients from the model, and return the standardized coefficients as a vector. An alternative would be to adapt the boot.sem() function in the sem package to return standardized coefficients. That might prove simpler for you. Regards, John -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of BdeGroot Sent: May-20-09 10:54 AM To: r-help@r-project.org Subject: Re: [R] SEM:Standard error of std.coef estimates? Dear John, Thank you for your reply. I would like to try the bootstrapping method. I have the boot package, however, I have not used it before. I do not know how to compute the correct code to calculate the standarized errors. If possible and easily achievable, could you please tell me what to do specifically or provide some more specific guidelines? Thanks, Bastiaan John Fox-6 wrote: Dear Bastiaan, The standard errors of the standardized coefficients aren't simple because the standard deviations used to standardize the coefficients are also subject to sampling error. I can think of two ways to get standard errors for the standardized coefficients: by the delta method and by bootstrapping. Neither method is implemented in the sem package. Figuring out how to apply the former would require some work; I'll put it on my to-do list, but may not get to it. The second approach could easily be implemented via the boot package. I hope this helps, John -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of BdeGroot Sent: May-20-09 7:41 AM To: r-help@r-project.org Subject: [R] SEM:Standard error of std.coef estimates? Hi, I am currently working with the sem package in R, to create pathway diagrams. Id like to use the standardized path coeffcients. To get these, I use std.coef. However, using this yields only the standardized coefficients, but does not give me the standard error. Does someone know how to get std.coef to show the standard error of the standardized path coefficients as well? Thanks, Bastiaan PS: When I use std.coef, all I get is this: std.coef(path.model.SSI4) Std. Estimate par1 par1 0.39499 com_veg --- tempm par2 par2 0.35231 SNutBili --- tempm par3 par3 -0.68170 S_SSI4 --- tempm par4 par4 -0.39145 com_veg --- Wdeficit par5 par5 -0.60025 SNutBili --- Wdeficit par6 par6 -0.20562 S_SSI4 --- Wdeficit par7 par7 0.14871 SNutBili --- com_veg par8 par8 0.14905 S_SSI4 --- com_veg par9 par9 -0.39164 S_SSI4 --- SNutBili -- View this message in context: http://www.nabble.com/SEM%3AStandard-error-of- std.coef-estimates--tp23633227p23633227.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/SEM%3AStandard-error-of- std.coef-estimates--tp23633227p23636945.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] How to load data from Statistics Canada
We would like to load data from Statistics Canada (http://www.statcan.gc.ca/) using R, for example, Employment and unemployment rates. It seems to me that the tables are displayed in HTML. I was wondering if you know how to load these tables. Thanks, -james __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Comparing spatial distributions - permutation test implementation
Hello everyone, I am looking at the joint spatial distribution of 2 kinds of organisms (estimated on a grid of points) and want to test for significant association or dissociation. My first question is: do you know a nice technique to do that, considering that I have a limited number of points (36) but that they are repeated (4 times)? I did GLMs to test for correlations between the two (hence forgetting about the spatial aspect of it) and was previously pointed to the SADIE software. Would there be anything explicitly spatial and available in R please? Then, Syrjala's test[1] seems appropriate and tests for differences in distribution. It computes a Cramér-von Mises-type statistic and tests its significance with a permutation test. I implemented the test in R and posted the code on these mailing lists[2]. Some people checked it and confirmed that the statistic gives correct results but my estimation of the p-value does not match the one predicted with the orignal software from Syrjala. I don't know what I am doing wrong. The permutation test is described by Syrjala as: (...) Under the null hypothesis, at a given sampling location (x_k, y_k), either density ob- servation y_i(x_k, y_k), i = 1, 2, is equally likely for each population. Thus, for a given data set, the distribution of the test statistic can be constructed by calculating the value of the test statistic for all 2^k pairwise per- mutations of the data set. (...) The level of signif- icance of a specific realization of the test statistic T is determined from its position in the ordered set of test statistic values from all 2^k permutations. (...) My understanding is that, for each permutation I should choose a random number of points (between 1 and k), swap the values for species 1 and species 2 at those points, and recompute the test on the new data. But this does not work :/ . Here is my code and associated data from Syrjala (for which I have reference values). Any advice would be very welcome (in particular if there is a way to leverage boot() for this). NB: computing the 1000 permutations can be a bit lengthy, but fortunately, by using plyr, you get a nice progress bar to look at! syrjala.stat - function(x, y=NULL, var1=NULL, var2=NULL) # # Compute Syrjala statistic # x, ycoordinates # var1, var2 value of 2 parameters both measured at (x,y) points # NB: x can also be a data.frame/matrix containing x,y,var1,var2 as columns # { # Input checks if (!is.null(ncol(x))) { if (ncol(x) == 4) { names(x) = c(x,y,var1,var2) dat = x } else { stop(Wrong number of columns in argument x) } } else { dat = data.frame(x, y, var1, var2) } # Normalize abundances dat$var1 = dat$var1/sum(dat$var1) dat$var2 = dat$var2/sum(dat$var2) # For each point (each line of dat) # compute the squared difference in gammas from each origin meanSqDiff = apply(dat, 1, function(d, coord, variab) { north = (coord$x=d[1]) east = (coord$y=d[2]) south = (coord$x=d[1]) west = (coord$y=d[2]) return( mean( c( (diff(sapply(variab[(north east),], sum)))^2, (diff(sapply(variab[(south east),], sum)))^2, (diff(sapply(variab[(south west),], sum)))^2, (diff(sapply(variab[(north west),], sum)))^2 ) ) ) }, dat[,c(x,y)], dat[,c(var1,var2)]) # Compute the statistic (i.e. sum of mean squared differences) return(sum(meanSqDiff)) } # Get data online : http://dl.getdropbox.com/u/1047321/syrjala_data_cod.csv system(curl http://dl.getdropbox.com/u/1047321/syrjala_data_cod.csv syrjala_data_cod.csv) dataCod = read.csv(file = syrjala_data_cod.csv, header = TRUE) # Normalize abundances dataCod$var1 = dataCod$var1/sum(dataCod$var1) dataCod$var2 = dataCod$var2/sum(dataCod$var2) # Number of permutations nperm = 1000 # Create nperm-1 replicates of the data (one is the original observation) d = rep(list(dataCod), nperm-1) # Compute number of observations before to avoid doing that for every replicate n = nrow(dataCod) require(plyr) # Permute some observations and compute the syrjala stat for each permutation psis = ldply(d, .fun=function(x, n){ # choose indices of observations to swap idx = sample(1:n, runif(1, min=1, max=n)) # swap observations x[idx, 3:4] = x[idx, 4:3] # compute syrjala stat return(syrjala.stat(x)) }, n, .progress=text) } # Compute the syrjala stat for the observations psi = syrjala.stat(dataCod) #
Re: [R] problem with APPLY
De France Henri wrote: Hello, The apply function seems to behave oddly with my code below NB : H1 is a data frame. (data in the attached file.) # the first lines are: 1 02/01/2008 0.00 0 0 0.00 0 2 03/01/2008 0.00 0 0 0.00 0 3 04/01/2008 0.00 0 0 0.00 0 4 07/01/2008 0.00 0 0 0.00 0 5 08/01/2008 0.00 0 0 0.00 0 6 09/01/2008 0.00 0 0 0.00 0 7 10/01/2008 0.00 0 0 0.00 0 8 11/01/2008 1.010391 0 0 1.102169 0 ... The aim of the code is to extract those lines for which there is a strictly positive value in the second column AND in one of the others: reper=function(x){as.numeric(x[2]1 any(x[3:length(x)]1))} TAB1= H1[which(apply(H1,1,reper)0),] Strangely, this is OK for all the lines, except for the last one. In fact, in H1, the last 2 lines are: 258 29/12/2008 1.476535 1.187615 0 0.00 0 259 30/12/2008 0.00 1.147888 0 0.00 0 Obviously, line 258 should be the last line of TAB1, but it is not the case (it does not appear at all) and I really don't understand why. This is all the more strange since applying the function reper only to this line 258 gives a 1 as expected... Can someone help ? Works for me... do...1. V3 V5 V7 V13 V31 213 24/10/2008 2.038218 2.820196 0 0.00 0 214 27/10/2008 3.356057 2.588509 0 2.101651 0 219 03/11/2008 2.122751 1.648410 0 2.180908 0 233 21/11/2008 1.439861 1.883605 0 1.359372 0 234 24/11/2008 1.216548 1.480797 0 1.049390 0 258 29/12/2008 1.476535 1.187615 0 0.00 0 You are crossing the creek to fetch water, though: reper - function(x) x[2]1 any(x[3:length(x)]1) TAB1 - H1[apply(H1,1,reper),] or even TAB1 - H1[ H1[2] 1 apply(H1[3:6] 1, 1, any),] -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - (p.dalga...@biostat.ku.dk) FAX: (+45) 35327907 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Supressing the enumeration of output in console
Hi! Pretty low content question but I've had major trouble finding an answer for it so I hope it's alright. I'm obviously new to R, and have been trying to get rid of the numerated output I get in the console. What I mean more specifically is that X-4;X comes out as [1] 4 and I'd like to get rid of the listing [1]. This isn't usually a problem when working with the console but when writing scripts that print out lines of text it gives a rather unattractive output in the console. Thanks in advance! Mike [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Class for time of day?
There is a times class in the chron package. Times are measured in fractions of a day so 1/24 is one hour. library(chron) dt - Sys.time() tt - times(format(dt, %H:%M:%S)) tt [1] 12:27:46 tt + 1/24 [1] 13:27:46 There is an article on dates and times in R News 4/1. On Wed, May 20, 2009 at 10:57 AM, Stavros Macrakis macra...@alum.mit.edu wrote: What is the recommended class for time of day (independent of calendar date)? And what is the recommended way to get the time of day from a POSIXct object? (Not a string representation, but a computable representation.) I have looked in the man page for DateTimeClasses, in the Time Series Analysis Task View and in Spector's Data Manipulation book but haven't found these. Clearly I can create my own Time class and hack around with the internal representation of POSIXct, e.g. days - unclass(d)/(24*3600) days-floor(days) and write print.Time, `-.Time`, etc. etc. but I expect there is already a standard class or CRAN package. -s [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] sem with categorical data
Dear Frank, Did you take a look at the data you generated? The contingency tables are extremely sparse. Try, e.g., with(dat, table(q1, q2)). (I assume, BTW, that you're using the cut2() function in the Hmisc package.) Beyond that, I'm not sure what the point is of your example. You're generating three independent lognormal random variables while the model assumed by polychoric correlation is of multinormal random variables; of course, these *could* be independent, but generally would not. I hope this helps, John On Wed, 20 May 2009 12:55:49 -0400 Frank Lawrence f...@psu.edu wrote: I am trying to run a confirmatory factor analysis using the SEM package. My data are ordinal. I have read http://socserv.mcmaster.ca/jfox/Misc/sem/SEM-paper.pdf. When I apply the hetcor function, I receive the following error: Error in checkmvArgs(lower = lower, upper = upper, mean = mean, corr = corr, : at least one element of 'lower' is larger than 'upper' Example: set.seed(781) q1 - cut2(x = rlnorm(n = 1e2, m = 2), cuts = seq(1,6)) q2 - cut2(x = rlnorm(n = 1e2, m = 0), cuts = seq(1,6)) q3 - cut2(x = rlnorm(n = 1e2, m = 1), cuts = seq(1,6)) dat - data.frame(q1,q2,q3) hetcor(data = dat, ML = T, pd = T, use = 'p') Any help in understanding and correcting the error would be appreciated. unlist(R.Version()) platform arch i386-pc-mingw32 i386 os system mingw32i386, mingw32 status major 2 minor year 9.0 2009 monthday 04 17 svn rev language 48333R version.string R version 2.9.0 (2009-04-17) Respectfully, Frank Lawrence John Fox, Professor Department of Sociology McMaster University Hamilton, Ontario, Canada http://socserv.mcmaster.ca/jfox/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Supressing the enumeration of output in console
Use the 'cat' function to put text on the console without any extra decoration (you are then responsible for all formatting including line feeds). Hope this helps, -- Gregory (Greg) L. Snow Ph.D. Statistical Data Center Intermountain Healthcare greg.s...@imail.org 801.408.8111 -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r- project.org] On Behalf Of ZeMajik Sent: Wednesday, May 20, 2009 1:04 PM To: r-help@r-project.org Subject: [R] Supressing the enumeration of output in console Hi! Pretty low content question but I've had major trouble finding an answer for it so I hope it's alright. I'm obviously new to R, and have been trying to get rid of the numerated output I get in the console. What I mean more specifically is that X-4;X comes out as [1] 4 and I'd like to get rid of the listing [1]. This isn't usually a problem when working with the console but when writing scripts that print out lines of text it gives a rather unattractive output in the console. Thanks in advance! Mike [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting- guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to google for R stuff?
I was having the same frustration so I made a Google custom search engine for Open Math Tools: http://www.google.com/coop/cse?cx=015659631714008342946:wolsniqtrxc It gives preferences to results from r-project.org, octave.org, maxima.sourceforge.net, and the mailing list archives from those projects. It also has some other smaller pages that contain tutorials for those tools. It includes results from the broader web as well, so if there is a highly ranked article from wikipedia or mathworld that will show up too. Here's a short write-up with example searches: http://j-stults.blogspot.com/2009/05/open-math-tools-custom-search-engine.html If any folks on the list out there have any suggestions or would like to be a 'contributor' on it post a reply with a site to add to the preference list , or click the 'volunteer to contribute' link on the search engine homepage. Good luck with your R searching. On Wed, May 20, 2009 at 9:02 AM, Kynn Jones kyn...@gmail.com wrote: Hi! I'm new to R programming, though I've been programming in other languages for years. One thing I find most frustrating about R is how difficult it is to use Google (or any other search tool) to look for answers to my R-related questions. With languages with even slightly more distinctive names like Perl, Java, Python, Matlab, OCaml, etc., usually including the name of the language in the query is enough to ensure that the top hits are relevant. But this trick does not work for R, because the letter R appears by itself in so many pages, that the chaff overwhelms the wheat, so to speak. So I'm curious to learn what strategies R users have found to get around this annoyance. TIA! KJ [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Joshua Stults Website: http://j-stults.blogspot.com __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Class for time of day?
If you want the hours from a POSIXct, here is one way of doing it; you can create a function for doing it: x - Sys.time() x [1] 2009-05-20 12:17:13 EDT y - difftime(x, trunc(x, units='days'), units='hours') y Time difference of 12.28697 hours as.numeric(y) [1] 12.28697 It depends on what type of computations you want to do with it. You can leave it as POSIXct and carry out a lot of them. Can you specify what you want? On Wed, May 20, 2009 at 10:57 AM, Stavros Macrakis macra...@alum.mit.eduwrote: What is the recommended class for time of day (independent of calendar date)? And what is the recommended way to get the time of day from a POSIXct object? (Not a string representation, but a computable representation.) I have looked in the man page for DateTimeClasses, in the Time Series Analysis Task View and in Spector's Data Manipulation book but haven't found these. Clearly I can create my own Time class and hack around with the internal representation of POSIXct, e.g. days - unclass(d)/(24*3600) days-floor(days) and write print.Time, `-.Time`, etc. etc. but I expect there is already a standard class or CRAN package. -s [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.htmlhttp://www.r-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Jim Holtman Cincinnati, OH +1 513 646 9390 What is the problem that you are trying to solve? [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to google for R stuff?
spencerg spencer.graves at prodsyse.com writes: de - RSiteSearch.function(differential equation) des - RSiteSearch.function(differential equations) # With de and des, each finds things missed by the other. de. - de | des # combine into one sumDE - packageSum2(de.) # add details on installed packages. Should be PackageSum2(de.) Dieter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to load data from Statistics Canada
g...@ucalgary.ca wrote: We would like to load data from Statistics Canada (http://www.statcan.gc.ca/) using R, for example, Employment and unemployment rates. It seems to me that the tables are displayed in HTML. I was wondering if you know how to load these tables. Thanks, -james __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Hi James, I believe a similar issue was covered recently in the following thread: http://www.nabble.com/import-HTML-tables-td23504282.html#a23517322 If this is not what you need, please go into more details as to what the issue at hand may be. HTH, -- *Luc Villandré* /Biostatistician McGill University Health Center - Montreal Children's Hospital Research Institute/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] dropping empty panels in xyplot
I note that someone asked for help a few weeks ago regarding the ability to drop empty panels on an xyplot. I did not see a reply to that inquiry so I am asking for assistance with the same problem To prepare the data for the plotting routine, I did the following to restrict the content of the data object to specific colonies of interest. Colony_HSI.df - Colony_HSI[Colony_HSI$Colony == NE Grossman A | Colony_HSI$Colony == Loop Road | Colony_HSI$Colony == Otter Creek | Colony_HSI$Colony == Upper Taylor Slough | Colony_HSI$Colony == Tamiami West ,] xyplot(Colony_HSI$MEAN + Colony_HSI$TotalNests ~ Colony_HSI$Year | Colony_HSI$Colony, lty=c(1,2), pch=c(1,9), par.settings = graph.sets, type = o, xlab= Year, ylim=c(0,1), ylab=Mean HSI, drop.unused.levels = lattice.getOption(drop.unused.levels)) However this produces a plot with 22 panels, but only 5 have data in them. Am I using the subsetting routines incorrectly? Why are there place holders in the data object even after I selected for just 5 of them? How can I build the plot including just the 5 colony names? Steve Steve Friedman Ph. D. Spatial Statistical Analyst Everglades and Dry Tortugas National Park 950 N Krome Ave (3rd Floor) Homestead, Florida 33034 steve_fried...@nps.gov Office (305) 224 - 4282 Fax (305) 224 - 4147 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] problem with APPLY
-Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of Peter Dalgaard Sent: Wednesday, May 20, 2009 8:16 AM To: De France Henri Cc: r-help@r-project.org Subject: Re: [R] problem with APPLY De France Henri wrote: Hello, The apply function seems to behave oddly with my code below NB : H1 is a data frame. (data in the attached file.) # the first lines are: 1 02/01/2008 0.00 0 0 0.00 0 2 03/01/2008 0.00 0 0 0.00 0 3 04/01/2008 0.00 0 0 0.00 0 4 07/01/2008 0.00 0 0 0.00 0 5 08/01/2008 0.00 0 0 0.00 0 6 09/01/2008 0.00 0 0 0.00 0 7 10/01/2008 0.00 0 0 0.00 0 8 11/01/2008 1.010391 0 0 1.102169 0 ... The aim of the code is to extract those lines for which there is a strictly positive value in the second column AND in one of the others: reper=function(x){as.numeric(x[2]1 any(x[3:length(x)]1))} TAB1= H1[which(apply(H1,1,reper)0),] Strangely, this is OK for all the lines, except for the last one. In fact, in H1, the last 2 lines are: 258 29/12/2008 1.476535 1.187615 0 0.00 0 259 30/12/2008 0.00 1.147888 0 0.00 0 Obviously, line 258 should be the last line of TAB1, but it is not the case (it does not appear at all) and I really don't understand why. This is all the more strange since applying the function reper only to this line 258 gives a 1 as expected... Can someone help ? Works for me... do...1. V3 V5 V7 V13 V31 213 24/10/2008 2.038218 2.820196 0 0.00 0 214 27/10/2008 3.356057 2.588509 0 2.101651 0 219 03/11/2008 2.122751 1.648410 0 2.180908 0 233 21/11/2008 1.439861 1.883605 0 1.359372 0 234 24/11/2008 1.216548 1.480797 0 1.049390 0 258 29/12/2008 1.476535 1.187615 0 0.00 0 You are crossing the creek to fetch water, though: reper - function(x) x[2]1 any(x[3:length(x)]1) TAB1 - H1[apply(H1,1,reper),] or even TAB1 - H1[ H1[2] 1 apply(H1[3:6] 1, 1, any),] -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - (p.dalga...@biostat.ku.dk) FAX: (+45) 35327907 I couldn't reproduce the bad result either. However, it was more or less by chance that the results were as good as they were. The call apply(myDataFrame, 1, FUN) does essentially the equivalent of myMatrix - as.matrix(myDataFrame) for(i in seq_len(nrow(myMatrix))) rowResult[i] - FUN(myMatrix[i,,drop=TRUE]) If myDataFrame contains any factor, character, POSIXt, or any other non-numeric columns then myMatrix will be a matrix of character strings. Each column of myDataFrame is passed though format() to make those strings, so the precise formatting of the strings depends on all the other elements of the column (E.g., one big or small number might cause the whole column to be formatted in scientific notation). Your reper() function happened to work because 2.3 0 is interpreted as (I think) 2.3 0 which is TRUE (at least in ASCII). However, if your cutoff were 0.02 then you might be surprised 2.30.02 [1] FALSE because as.character(0.02) is 2e-06. I think that using apply(MARGIN=1,...) to data.frames is generally a bad idea and it only really works if all the columns are the same simple type. Avoiding it altgether makes for tedious coding like H1[ H1[2] 1 (H1[,3]1 | H1[,4]1 | H1[,5]1 | H1[,6]1) ,] You can also use pmax (parallel max), as in, H1[H1[2]1 do.call(pmax, unname(as.list(H1[,3:6])))1, ] Peter's 2nd solution calls apply(MARGIN=1,...) only on the numeric part of the data.frame so it works as expected. Bill Dunlap TIBCO Software Inc - Spotfire Division wdunlap tibco.com __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Where to find a changelog for the survival package
Thank you Richie. I had seen this before, but my impression is that it's not up to date. I gave a wrong version number in my previous post. I changed from 2.34-1 to 2.35-4. For example, the plot.survfit function lost it's legend parameters, but I don't see this in the changelog. Thanks again, Heinz At 14:53 20.05.2009, richard.cot...@hsl.gov.uk wrote: since some days I try to use the versions 2.35-4 of the survival package instead of versions 2.31, I had installed until now. Several changes in print.survfit, plot.survfit and seemingly in the structure of ratetabels effect some of my syntax files. Is there somewhere a documentation of these changes, besides the code itself? It's in the repository on R-Forge. The latest version is here: http://r-forge.r-project.org/plugins/scmsvn/viewcvs.php/pkg/survival/Changelog.09?rev=11234root=survivalview=markup Regards, Richie. Mathematical Sciences Unit HSL ATTENTION: This message contains privileged and confidential information intended for the addressee(s) only. If this message was sent to you in error, you must not disseminate, copy or take any action in reliance on it and we request that you notify the sender immediately by return email. Opinions expressed in this message and any attachments are not necessarily those held by the Health and Safety Laboratory or any person connected with the organisation, save those by whom the opinions were expressed. Please note that any messages sent or received by the Health and Safety Laboratory email system may be monitored and stored in an information retrieval system. Scanned by MailMarshal - Marshal's comprehensive email content security solution. Download a free evaluation of MailMarshal at www.marshal.com __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to load data from Statistics Canada
Yes, XML can help load HTML tables. As we knew, tables in Bureau of Labor Statistics (http://www.bls.gov/) can be displayed in HTML and can also be loaded directly using their urls, for example, ftp://ftp.bls.gov/pub/time.series/wp/ I was wondering if tables in Statist Canada have such locations so that we load them directly. Thanks, -james g...@ucalgary.ca wrote: We would like to load data from Statistics Canada (http://www.statcan.gc.ca/) using R, for example, Employment and unemployment rates. It seems to me that the tables are displayed in HTML. I was wondering if you know how to load these tables. Thanks, -james __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Hi James, I believe a similar issue was covered recently in the following thread: http://www.nabble.com/import-HTML-tables-td23504282.html#a23517322 If this is not what you need, please go into more details as to what the issue at hand may be. HTH, -- *Luc Villandré* /Biostatistician McGill University Health Center - Montreal Children's Hospital Research Institute/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to load data from Statistics Canada
g...@ucalgary.ca wrote: We would like to load data from Statistics Canada (http://www.statcan.gc.ca/) using R, for example, Employment and unemployment rates. It seems to me that the tables are displayed in HTML. I was wondering if you know how to load these tables. Thanks, I suspect the answer is with some difficulty. You can do stuff like this, based on using the clipboard. Go to http://www.statcan.gc.ca/daily-quotidien/090520/t090520b1-eng.htm mark the contents of the table, then dd - t(read.delim(clipboard, colClasses=character)) dd1 - dd[-1,] # 1st row are labels dd2 - as.numeric(gsub(,,,dd1)) # strip thousands separators Warning message: NAs introduced by coercion dim(dd2) - dim(dd1) dd2 [,1] [,2] [,3] [,4][,5] [,6] [,7] [,8] [,9] [,10] [,11] [1,] NA 226.8 123.1 2948.0 11630.0 178768.0 122.5 NA 37.6 27822.0 1.760 [2,] NA 224.6 117.7 2945.0 10709.0 181862.0 121.7 NA 37.1 28822.0 1.750 [3,] NA 222.0 109.5 2932.0 9694.0 185068.0 121.1 NA 36.9 27801.0 1.730 [4,] NA 218.8 101.2 2924.0 8968.0 187636.0 120.6 NA 36.7 26560.0 1.690 [5,] NA 215.6 97.2 2920.0 8759.0 189702.0 120.1 NA 36.4 23762.0 1.640 [6,] NA 213.3 96.0 2918.0 8770.0 191343.0 119.7 NA 36.2 22029.0 1.600 [7,] NA -1.1 -1.2 -0.1 0.1 0.9 -0.3 NA -0.5-7.3 -0.045 [,12] [,13] [,14] [,15] [1,]NA 2959.0 9637.0 221.8 [2,]NA 2963.0 9635.0 218.4 [3,]NA 2966.0 9587.0 217.1 [4,]NA 2939.0 9368.0 211.2 [5,]NA 2915.0 9325.0 209.4 [6,]NA 2879.0 9199.0 210.5 [7,]NA -1.2 -1.4 0.5 -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - (p.dalga...@biostat.ku.dk) FAX: (+45) 35327907 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Linear constraints for constrasts
Dear List! How can I define contrasts (design matrix) that can all be included, i.e. which do not require a control category be dropped. My application (see below) does not suggest a sensible control category. I am thinking of constraining the (treatment) contrasts to sum up to zero and dropping the constant term in the regression. Is this a good idea? If yes, how to achieve this in R? I am estimating a GLM for bilateral country data. Each observation in on a pair of countries, e.g. GER_USA, GER_JAP, USA_JAP. I constructed the following contrasts: d_GER, d_USA, d_JAP, which take the value of 1 when the country is in the pair and 0 otherwise, i.e. “Bilat”, “d_GER”, “d_USA”, “d_JAP” GER_USA, 1, 1, 0 GER_JAP, 1, 0, 1 USA_JAP, 0, 1, 1 These contrasts highlight the effect of having a given country in the pair. Thank you for your help! Serguei Kaniovski __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] minmun p-value for wilcox.test and correlation
I have a stupid question on how to get the real p-values for wilcox.test and correlation. the minmun can be reached is 2.2E-16 using the R version 2.6.2. I do not think it is the R version causing this but other issues. Any help is highly appreciated. Charles -- View this message in context: http://www.nabble.com/minmun-p-value-for-wilcox.test-and-correlation-tp23637568p23637568.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Predicting complicated GAMMs on response scale
Creation of Animal category in p.d solved all problems. Plots fine now. The smallest hurdles are often the hardest to get over. Gavin Simpson wrote: On Mon, 2009-05-18 at 11:48 -0700, William Paterson wrote: Hi, I am using GAMMs to show a relationship of temperature differential over time with a model that looks like this:- gamm(Diff~s(DaysPT)+AirToC,method=REML) where DaysPT is time in days since injury and Diff is repeat measures of temperature differentials with regards to injury sites compared to non-injured sites in individuals over the course of 0-24 days. I use the following code to plot this model on the response scale with 95% CIs which works fine:- g.m-gamm(Diff~s(DaysPT)+AirToC,method=REML) p.d-data.frame(DaysPT=seq(min(DaysPT),max(DaysPT))) p.d$AirToC-(6.7) b-predict.gam(g.m$gam,p.d,se=TRUE) range-c(min(b$fit-2*b$se.fit),max(b$fit+2*b$se.fit)) plot(p.d$DaysPT,b$fit,ylim=c(-4,12),xlab=Days post-tagging,ylab=dTmax (ºC),type=l,lab=c(24,4,12),las=1,cex.lab=1.5, cex.axis=1,lwd=2) lines(p.d$DaysPT,b$fit+b$se.fit*1.96,lty=2,lwd=1.5) lines(p.d$DaysPT,b$fit-b$se.fit*1.96,lty=2,lwd=1.5) points(DaysPT,Diff) However, when I add a correlation structure and/or a variance structure so that the model may look like:- gamm(Diff~s(DaysPT3)+AirToC,correlation=corCAR1(form=~DaysPT| Animal),weights=varPower(form=~DaysPT),method=REML) I get this message at the point of inputting the line b-predict.gam(g.m$gam,p.d,se=TRUE) Note that p.d doesn't contain Animal. Not sure this is the problem, but I would have thought you'd need to supply new values of Animal for the data you wish to predict for in order to get the CAR(1) errors correct. Is it possible that the model is finding another Animal variable in the global environment? I have predicted from several thousand GAMMs containing correlation structures similar to the way you do above so this does work in general. If the above change to p.d doesn't work, you'll probably need to speak to Simon Wood to take this further. Is mgcv up-to-date? I am using 1.5-5 that was released in the last week or so. For example, this dummy example runs without error for me and is similar to your model y1 - arima.sim(list(order = c(1,0,0), ar = 0.5), n = 200, sd = 1) y2 - arima.sim(list(order = c(1,0,0), ar = 0.8), n = 200, sd = 3) x1 - rnorm(200) x2 - rnorm(200) ind - rep(1:2, each = 200) d - data.frame(Y = c(y1,y2), X = c(x1,x2), ind = ind, time = rep(1:200, times = 2)) require(mgcv) mod - gamm(Y ~ s(X), data = d, corr = corCAR1(form = ~ time | ind), weights = varPower(form = ~ time)) p.d - data.frame(X = rep(seq(min(d$X), max(d$X), len = 20), 2), ind = rep(1:2, each = 20), time = rep(1:20, times = 2)) pred - predict(mod$gam, newdata = p.d, se = TRUE) Does this work for you? If not, the above would be a reproducible example (as asked for in the posting guide) and might help Simon track down the problem if you are running an up-to-date mgcv. HTH G Error in model.frame(formula, rownames, variables, varnames, extras, extranames, : variable lengths differ (found for 'DaysPT') In addition: Warning messages: 1: not all required variables have been supplied in newdata! in: predict.gam(g.m$gam, p.d, se = TRUE) 2: 'newdata' had 25 rows but variable(s) found have 248 rows Is it possible to predict a more complicated model like this on the response scale? How can I incorporate a correlation structure and variance structure in a dataframe when using the predict function for GAMMs? Any help would be greatly appreciated. William Paterson -- %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% Dr. Gavin Simpson [t] +44 (0)20 7679 0522 ECRC, UCL Geography, [f] +44 (0)20 7679 0565 Pearson Building, [e] gavin.simpsonATNOSPAMucl.ac.uk Gower Street, London [w] http://www.ucl.ac.uk/~ucfagls/ UK. WC1E 6BT. [w] http://www.freshwaters.org.uk %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/Predicting-complicated-GAMMs-on-response-scale-tp23603248p23639184.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] sem with categorical data
I am trying to run a confirmatory factor analysis using the SEM package. My data are ordinal. I have read http://socserv.mcmaster.ca/jfox/Misc/sem/SEM-paper.pdf. When I apply the hetcor function, I receive the following error: Error in checkmvArgs(lower = lower, upper = upper, mean = mean, corr = corr, : at least one element of 'lower' is larger than 'upper' Example: set.seed(781) q1 - cut2(x = rlnorm(n = 1e2, m = 2), cuts = seq(1,6)) q2 - cut2(x = rlnorm(n = 1e2, m = 0), cuts = seq(1,6)) q3 - cut2(x = rlnorm(n = 1e2, m = 1), cuts = seq(1,6)) dat - data.frame(q1,q2,q3) hetcor(data = dat, ML = T, pd = T, use = 'p') Any help in understanding and correcting the error would be appreciated. unlist(R.Version()) platform arch i386-pc-mingw32 i386 os system mingw32i386, mingw32 status major 2 minor year 9.0 2009 monthday 04 17 svn rev language 48333R version.string R version 2.9.0 (2009-04-17) Respectfully, Frank Lawrence __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] error message re: max(i), but code and output seen O.K.
I have a researcher who is consistently get the warning message: In max(i) : no non-missing arguments to max; returning -Inf Best as I can tell the code is working properly and the output is as expected. I would like some help in understanding why he is getting this error message and what its implications are. I have his code. Sincerely, Kirsten Miles Support Specialist Research Computing Lab Charles L. Brown Science and Engineering Library kd...@virginia.edu [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Example for parsing XML file?
Hi, I am trying to parse XML files and read them into R as a data frame, but have been unable to find examples which I could apply successfully. I'm afraid I don't know much about XML, which makes this all the more difficult. If someone could point me in the right direction to a resource (preferably with an example or two), it would be greatly appreciated. Here is a snippet from one of the XML files that I am looking to read, and I am aiming to be able to get it into a data frame with columns N, T, A, B, C as in the 2nd level of the heirarchy. ?xml version=1.0 encoding=utf-8 ? - C S=UnitA D=1/3/2007 C=24745 F=24648 T N=1 T=9:30:13 AM A=30.05 B=29.85 C=30.05 / T N=2 T=9:31:05 AM A=29.89 B=29.78 C=30.05 / T N=3 T=9:31:05 AM A=29.9 B=29.86 C=29.87 / T N=4 T=9:31:05 AM A=29.86 B=29.86 C=29.87 / T N=5 T=9:31:05 AM A=29.89 B=29.86 C=29.87 / T N=6 T=9:31:06 AM A=29.89 B=29.85 C=29.86 / T N=7 T=9:31:06 AM A=29.89 B=29.85 C=29.86 / T N=8 T=9:31:06 AM A=29.89 B=29.85 C=29.86 / /C Thanks for any help or direction anyone can provide. As a point of reference, I am using R 2.8.1 and have loaded the XML package. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Non-linear regression with latent variable
Hi Can anyone please suggest me a package where I can estimate a non-linear regression model? One of the independent variables is latent or unobserved. I have an indicator variable for this unobserved variable; however the relationship is known to be non-linear also. In terms of equations my problem is y=f(latent, fixed) q=g(latent) where q is the indicator variable For me both f and g are non-linear. Thanks Samiul Hasan -- View this message in context: http://www.nabble.com/Non-linear-regression-with-latent-variable-tp23641833p23641833.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] minmun p-value for wilcox.test and correlation
charles78 hu...@hotmail.com wrote I have a stupid question on how to get the real p-values for wilcox.test and correlation. the minmun can be reached is 2.2E-16 using the R version 2.6.2. I do not think it is the R version causing this but other issues. Any help is highly appreciated. Can I ask why you want this? I'm curious. Peter Peter L. Flom, PhD Statistical Consultant www DOT peterflomconsulting DOT com __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] round function seems to produce maximum 2 decimals
I am trying to use round()to force R to display a specific number of decimals, but it seems to display =2 decimals no matter what I specify in the digits argument. As an alternative I tried signif(), but it also produces unexpected results. See example code and results below. Format() works, but then the result no longer is numeric. Am I missing something simple? I am using R 2.9.0 on Windows XP. Thanks, Glenn #code h=12345.16711 h round(h,digits=1) round(h,digits=2) round(h,digits=3) round(h,digits=4) round(h,digits=5) signif(h,digits=9) format(h,nsmall=4) #results h=12345.16711 h [1] 12345.17 round(h,digits=1) [1] 12345.2 round(h,digits=2) [1] 12345.17 round(h,digits=3) [1] 12345.17 round(h,digits=4) [1] 12345.17 round(h,digits=5) [1] 12345.17 signif(h,digits=9) [1] 12345.17 format(h,nsmall=4) [1] 12345.1671 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to load data from Statistics Canada
Peter Dalgaard wrote: g...@ucalgary.ca wrote: We would like to load data from Statistics Canada (http://www.statcan.gc.ca/) using R, for example, Employment and unemployment rates. It seems to me that the tables are displayed in HTML. I was wondering if you know how to load these tables. Thanks, I suspect the answer is with some difficulty. You can do stuff like this, based on using the clipboard. Go to or maybe library(XML) document = htmlParse('http://www.statcan.gc.ca/daily-quotidien/090520/t090520b1-eng.htm') rows = xpathSApply(document, '//table/tbody/tr') and then use further xpaths to extract the content of interest. vQ http://www.statcan.gc.ca/daily-quotidien/090520/t090520b1-eng.htm mark the contents of the table, then dd - t(read.delim(clipboard, colClasses=character)) dd1 - dd[-1,] # 1st row are labels dd2 - as.numeric(gsub(,,,dd1)) # strip thousands separators Warning message: NAs introduced by coercion dim(dd2) - dim(dd1) dd2 [,1] [,2] [,3] [,4][,5] [,6] [,7] [,8] [,9] [,10] [,11] [1,] NA 226.8 123.1 2948.0 11630.0 178768.0 122.5 NA 37.6 27822.0 1.760 [2,] NA 224.6 117.7 2945.0 10709.0 181862.0 121.7 NA 37.1 28822.0 1.750 [3,] NA 222.0 109.5 2932.0 9694.0 185068.0 121.1 NA 36.9 27801.0 1.730 [4,] NA 218.8 101.2 2924.0 8968.0 187636.0 120.6 NA 36.7 26560.0 1.690 [5,] NA 215.6 97.2 2920.0 8759.0 189702.0 120.1 NA 36.4 23762.0 1.640 [6,] NA 213.3 96.0 2918.0 8770.0 191343.0 119.7 NA 36.2 22029.0 1.600 [7,] NA -1.1 -1.2 -0.1 0.1 0.9 -0.3 NA -0.5-7.3 -0.045 [,12] [,13] [,14] [,15] [1,]NA 2959.0 9637.0 221.8 [2,]NA 2963.0 9635.0 218.4 [3,]NA 2966.0 9587.0 217.1 [4,]NA 2939.0 9368.0 211.2 [5,]NA 2915.0 9325.0 209.4 [6,]NA 2879.0 9199.0 210.5 [7,]NA -1.2 -1.4 0.5 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] error message re: max(i), but code and output seen O.K.
This error is thrown if the argument to max is either NULL or length zero: [~] Rscript -e max(NULL) [1] -Inf Warning message: In max(NULL) : no non-missing arguments to max; returning -Inf [~] Rscript -e max(numeric(0)) [1] -Inf Warning message: In max(numeric(0)) : no non-missing arguments to max; returning -Inf HTH, --sundar On Wed, May 20, 2009 at 11:23 AM, Kirsten Miles sirole@gmail.com wrote: I have a researcher who is consistently get the warning message: In max(i) : no non-missing arguments to max; returning -Inf Best as I can tell the code is working properly and the output is as expected. I would like some help in understanding why he is getting this error message and what its implications are. I have his code. Sincerely, Kirsten Miles Support Specialist Research Computing Lab Charles L. Brown Science and Engineering Library kd...@virginia.edu [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] minmun p-value for wilcox.test and correlation
charles78 wrote: I have a stupid question on how to get the real p-values for wilcox.test and correlation. the minmun can be reached is 2.2E-16 using the R version 2.6.2. I do not think it is the R version causing this but other issues. Any help is highly appreciated. Charles It's mainly a printing issue (and to some extent historical, because small p-values in the upper tail were generated by subtraction and could underflow if 2.2e-16): wilcox.test(1:100,101:200) Wilcoxon rank sum test with continuity correction data: 1:100 and 101:200 W = 0, p-value 2.2e-16 alternative hypothesis: true location shift is not equal to 0 wilcox.test(1:100,101:200)$p.value [1] 2.562144e-34 -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - (p.dalga...@biostat.ku.dk) FAX: (+45) 35327907 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] error message re: max(i), but code and output seen O.K.
On 21/05/2009, at 6:23 AM, Kirsten Miles wrote: I have a researcher who is consistently get the warning message: In max(i) : no non-missing arguments to max; returning -Inf Best as I can tell the code is working properly and the output is as expected. I would like some help in understanding why he is getting this error message and what its implications are. I have his code. (a) This is not an error message, it is a warning message. (b) The message says that, in a particular context, all of the arguments to max() are missing. Hence you are taking the maximum of the empty set. By definition this maximum is -infinity. (This makes good sense when you think about it carefully.) (c) What the implications are is hard to say without knowing what the code is actually doing. You say that the output is as expected; this *probably* means that the definition of the maximum of the empty set is meshing as it should with the remainder of the calculations. However if I were doing it, I'd track down the instance where all of the arguments to max are missing and make sure that the code really is doing the right thing. You have to decide what *is* the right thing. What *should* happen if all of the arguments are NA? One way to start tracking down the instance would be to set options(warn=2) to change the warning to a real error, and then use traceback() to see where the error occurred. cheers, Rolf Turner ## Attention:\ This e-mail message is privileged and confid...{{dropped:9}} __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to google for R stuff?
Thank you all very much for the so many useful ideas and resources. KJ [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] how to get remote ESS graphics to work?
Hi all, My graduate student is logging onto my macpro and running R through ESS aquamacs (with Mx ssh and then Mx ess-remote). Everything is working fine until we get to graphing. We are trying to give him the ability to look at graphics interactively. The ESS manual is not too helpful: If you run X11 (See Section 13.3.2 [X11], page 68, X-windows) on both the local and remote machines then you should be able to display the graphs locally by setting the ‘DISPLAY’ environment variable appropriately. It's unclear what DISPLAY is appropriate. I have X11 forwarding set up on my machine (the remote machine). When we try to create a graphic in his ESS remote process, (e.g., hist(rnorm(50))), we get the following error: Error in X11(... unable to start device X11cairo In addition: Warning message: In x11(): unable to open connection to X11 display Does anyone out there use interactive graphics on their ESS remote sessions? If so, could you provide any help? We're really stuck and just need a step-by-step from anyone who knows. Thank you, Matt -- Matthew C Keller Asst. Professor of Psychology University of Colorado at Boulder www.matthewckeller.com __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Example for parsing XML file?
Hi Brigid. Here are a few commands that should do what you want: bri = xmlParse(myDataFile.xml) tmp = t(xmlSApply(xmlRoot(bri), xmlAttrs))[, -1] dd = as.data.frame(tmp, stringsAsFactors = FALSE, row.names = 1:nrow(tmp)) And then you can convert the columns to whatever types you want using regular R commands. The basic idea is that for each of the child nodes of C, i.e. the T's, we want the character vector of attributes which we can get with xmlAttrs(). Then we stack them together into a matrix, drop the N and then convert the result to a data frame, avoiding duplicate row names which are all T. (BTW, make certain the '-' on the second line is not in the XML content. I assume that came from bringing the text into mail.) HTH D. Brigid Mooney wrote: Hi, I am trying to parse XML files and read them into R as a data frame, but have been unable to find examples which I could apply successfully. I'm afraid I don't know much about XML, which makes this all the more difficult. If someone could point me in the right direction to a resource (preferably with an example or two), it would be greatly appreciated. Here is a snippet from one of the XML files that I am looking to read, and I am aiming to be able to get it into a data frame with columns N, T, A, B, C as in the 2nd level of the heirarchy. ?xml version=1.0 encoding=utf-8 ? - C S=UnitA D=1/3/2007 C=24745 F=24648 T N=1 T=9:30:13 AM A=30.05 B=29.85 C=30.05 / T N=2 T=9:31:05 AM A=29.89 B=29.78 C=30.05 / T N=3 T=9:31:05 AM A=29.9 B=29.86 C=29.87 / T N=4 T=9:31:05 AM A=29.86 B=29.86 C=29.87 / T N=5 T=9:31:05 AM A=29.89 B=29.86 C=29.87 / T N=6 T=9:31:06 AM A=29.89 B=29.85 C=29.86 / T N=7 T=9:31:06 AM A=29.89 B=29.85 C=29.86 / T N=8 T=9:31:06 AM A=29.89 B=29.85 C=29.86 / /C Thanks for any help or direction anyone can provide. As a point of reference, I am using R 2.8.1 and have loaded the XML package. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Example for parsing XML file?
Brigid Mooney wrote: Hi, I am trying to parse XML files and read them into R as a data frame, but have been unable to find examples which I could apply successfully. I'm afraid I don't know much about XML, which makes this all the more difficult. If someone could point me in the right direction to a resource (preferably with an example or two), it would be greatly appreciated. Here is a snippet from one of the XML files that I am looking to read, and I am aiming to be able to get it into a data frame with columns N, T, A, B, C as in the 2nd level of the heirarchy. There might be a simpler approach, but this seems to do: library(XML) input = xmlParse( '?xml version=1.0 encoding=utf-8 ? C S=UnitA D=1/3/2007 C=24745 F=24648 T N=1 T=9:30:13 AM A=30.05 B=29.85 C=30.05 / T N=2 T=9:31:05 AM A=29.89 B=29.78 C=30.05 / T N=3 T=9:31:05 AM A=29.9 B=29.86 C=29.87 / T N=4 T=9:31:05 AM A=29.86 B=29.86 C=29.87 / T N=5 T=9:31:05 AM A=29.89 B=29.86 C=29.87 / T N=6 T=9:31:06 AM A=29.89 B=29.85 C=29.86 / T N=7 T=9:31:06 AM A=29.89 B=29.85 C=29.86 / T N=8 T=9:31:06 AM A=29.89 B=29.85 C=29.86 / /C') (output = data.frame(t(xpathSApply(input, '//T', xpathSApply, '@*' # N T A B C # 1 1 9:30:13 AM 30.05 29.85 30.05 # 2 2 9:31:05 AM 29.89 29.78 30.05 # 3 3 9:31:05 AM 29.9 29.86 29.87 # 4 4 9:31:05 AM 29.86 29.86 29.87 # 5 5 9:31:05 AM 29.89 29.86 29.87 # 6 6 9:31:06 AM 29.89 29.85 29.86 # 7 7 9:31:06 AM 29.89 29.85 29.86 # 8 8 9:31:06 AM 29.89 29.85 29.86 output$N # [1] 1 2 3 4 5 6 7 8 # Levels: 1 2 3 4 5 6 7 8 you may need to reformat the columns. vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to google for R stuff?
Le mercredi 20 mai 2009 à 09:02 -0400, Kynn Jones a écrit : Hi! I'm new to R programming, though I've been programming in other languages for years. One thing I find most frustrating about R is how difficult it is to use Google (or any other search tool) to look for answers to my R-related questions. With languages with even slightly more distinctive names like Perl, Java, Python, Matlab, OCaml, etc., usually including the name of the language in the query is enough to ensure that the top hits are relevant. But this trick does not work for R, because the letter R appears by itself in so many pages, that the chaff overwhelms the wheat, so to speak. So I'm curious to learn what strategies R users have found to get around this annoyance. ISTR having this question or very close ones at least thrice in the last two months. Time for a FAQ entry ? (It does not seem to exist : I checked...) Emmanuel Charpentier __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] combining xYplot with map
I'm using xYplot to create a bubble plot of values that I'd like to visualize on top of a filled-in map of the coast, but I'm too much of a lattice (which I understand xYplot is built on) and mapping newbie to figure out how to begin to make this happen. Below is some sample code that doesn't work but illustrates my goal. Any pointers anyone has would be much appreciated. I'm using R v2.9.0 on Windows with Hmisc v3.6-0 and maps v2.1-0. Cheers, eric library(Hmisc) library(maps) sample.data - data.frame(lat = c(12.1667, 14.6333, -6.874, 2.6167, 14.6833, 11.2, 3.2667, 11.4167, -13.8623, 13.1667), lon = c(-126.25, -103.4667, -88.4572, -93.65, -97.7, -88.65, -111.0167, -119.7333, -100.0748, -108.0333), exp.index = c(23.6266244576543, 2.06824648038330, 0, 1.46378849121688, 24.1824663424805, 0, 0.364600074527829, 4.468039274638, 0.543833744085446, 18.2301918845932)) xlim - c(-150, -80) ylim - c(-5, 30) print(xYplot(lat ~ lon, data = sample.data, size = sample.data$exp.index, xlim = xlim, ylim = ylim )) map(world, fill = TRUE, col = gray, xlim = xlim, ylim = ylim, add = TRUE) -- Eric Archer, Ph.D. Southwest Fisheries Science Center National Marine Fisheries Service North Torrey Pines Court La Jolla, CA 92037-1022 858-546-7121 (work) 858-546-7003 (FAX) ETP Cetacean Assessment Program: http://swfsc.noaa.gov/prd-etp.aspx Population ID Program: http://swfsc.noaa.gov/prd-popid.aspx Innocence about Science is the worst crime today. - Sir Charles Percy Snow Lighthouses are more helpful than churches. - Benjamin Franklin ...but I'll take a GPS over either one. - John C. Craig George __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] round function seems to produce maximum 2 decimals
On 20-May-09 20:10:15, Glenn E Stauffer wrote: I am trying to use round()to force R to display a specific number of decimals, but it seems to display =2 decimals no matter what I specify in the digits argument. As an alternative I tried signif(), but it also produces unexpected results. See example code and results below. Format() works, but then the result no longer is numeric. Am I missing something simple? I am using R 2.9.0 on Windows XP. Thanks, Glenn #code h=12345.16711 h round(h,digits=1) round(h,digits=2) round(h,digits=3) round(h,digits=4) round(h,digits=5) signif(h,digits=9) format(h,nsmall=4) #results h=12345.16711 h [1] 12345.17 round(h,digits=1) [1] 12345.2 round(h,digits=2) [1] 12345.17 round(h,digits=3) [1] 12345.17 round(h,digits=4) [1] 12345.17 round(h,digits=5) [1] 12345.17 signif(h,digits=9) [1] 12345.17 format(h,nsmall=4) [1] 12345.1671 What you're missing is that when you do (e.g.) h - 12345.16711 round(h,digits=4) # [1] 12345.17 what is displayed ([1] 12345.17) is not the result of round(), but what the result of round() is to be displayed as given the options digits=7 (default) for the number of *significant figures* in the display of stored values. To see the result as it is stored, you should use print() with the appropriate number of disgits specified: print( round(h,digits=5),10) # [1] 12345.16711 print( round(h,digits=4),10) # [1] 12345.1671 print( round(h,digits=3),10) # [1] 12345.167 print( round(h,digits=2),10) # [1] 12345.17 Internally, round(h) is correctly stored: h4 - round(h,4) h - h4 # [1] 1e-05 h3 - round(h,3) h - h3 # [1] 0.00011 h2 - round(h,2) h - h2 # [1] -0.00289 To illustrate the influence of the display option digits=7: h-45.16711 h # [1] 45.16711 round(h,digits=4) # [1] 45.1671 round(h,digits=3) # [1] 45.167 round(h,digits=2) # [1] 45.17 h-345.16711 h # [1] 345.1671 round(h,digits=4) # [1] 345.1671 round(h,digits=3) # [1] 345.167 round(h,digits=2) # [1] 345.17 h-2345.16711 h # [1] 2345.167 round(h,digits=4) # [1] 2345.167 round(h,digits=3) # [1] 2345.167 round(h,digits=2) # [1] 2345.17 Hoping this helps, Ted. E-Mail: (Ted Harding) ted.hard...@manchester.ac.uk Fax-to-email: +44 (0)870 094 0861 Date: 20-May-09 Time: 22:54:41 -- XFMail -- __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] round function seems to produce maximum 2 decimals
Glenn E Stauffer wrote: I am trying to use round()to force R to display a specific number of decimals, but it seems to display =2 decimals no matter what I specify in the digits argument. As an alternative I tried signif(), but it also produces unexpected results. See example code and results below. Format() works, but then the result no longer is numeric. Am I missing something simple? I am using R 2.9.0 on Windows XP. Thanks, Glenn #code h=12345.16711 h round(h,digits=1) round(h,digits=2) round(h,digits=3) round(h,digits=4) round(h,digits=5) signif(h,digits=9) format(h,nsmall=4) #results h=12345.16711 h [1] 12345.17 round(h,digits=1) [1] 12345.2 round(h,digits=2) [1] 12345.17 round(h,digits=3) [1] 12345.17 round(h,digits=4) [1] 12345.17 round(h,digits=5) [1] 12345.17 signif(h,digits=9) [1] 12345.17 format(h,nsmall=4) [1] 12345.1671 options(digits) is set to 7 by default. h - 12345.16711 round(h,digits=5) [1] 12345.17 print(h,digits=12) [1] 12345.16711 options(digits=12) round(h,digits=5) [1] 12345.16711 round(h,digits=4) [1] 12345.1671 round(h,digits=3) [1] 12345.167 round(h,digits=2) [1] 12345.17 -- View this message in context: http://www.nabble.com/round-function-seems-to-produce-maximum-2-decimals-tp23643311p23643853.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] error message re: max(i), but code and output seen O.K.
On Wed, 20 May 2009, Kirsten Miles wrote: I have a researcher who is consistently get the warning message: In max(i) : no non-missing arguments to max; returning -Inf You get this message when trying to take the maximum of a vector with no elements. I am guessing he is looping through and in some cases getting an empty vector. x - numeric(0) max(x) [1] -Inf Warning message: In max(x) : no non-missing arguments to max; returning -Inf David Scott Best as I can tell the code is working properly and the output is as expected. I would like some help in understanding why he is getting this error message and what its implications are. I have his code. Sincerely, Kirsten Miles Support Specialist Research Computing Lab Charles L. Brown Science and Engineering Library kd...@virginia.edu [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. _ David Scott Department of Statistics The University of Auckland, PB 92019 Auckland 1142,NEW ZEALAND Phone: +64 9 923 5055, or +64 9 373 7599 ext 85055 Email: d.sc...@auckland.ac.nz, Fax: +64 9 373 7018 Graduate Officer, Department of Statistics Director of Consulting, Department of Statistics __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] combining xYplot with map
I'll retract my request for help. I managed to solve the problem by calling map followed by a call to points after rescaling the cex. Its the kind of solution that deserves a head-slap. library(Hmisc) library(maps) sample.data - data.frame(lat = c(12.1667, 14.6333, -6.874, 2.6167, 14.6833, 11.2, 3.2667, 11.4167, -13.8623, 13.1667), lon = c(-126.25, -103.4667, -88.4572, -93.65, -97.7, -88.65, -111.0167, -119.7333, -100.0748, -108.0333), exp.index = c(23.6266244576543, 2.06824648038330, 0, 1.46378849121688, 24.1824663424805, 0, 0.364600074527829, 4.468039274638, 0.543833744085446, 18.2301918845932)) xlim - c(-150, -80) ylim - c(-5, 30) cex.range - c(1, 5) exp.range - range(sample.data$exp.index) exp.cex - diff(cex.range) * sample.data$exp.index / exp.range[2] + cex.range[1] map(world, fill = TRUE, col = gray, xlim = xlim, ylim = ylim) points(sample.data$lon, sample.data$lat, pch = 21, cex = exp.cex) eric.archer wrote: I'm using xYplot to create a bubble plot of values that I'd like to visualize on top of a filled-in map of the coast, but I'm too much of a lattice (which I understand xYplot is built on) and mapping newbie to figure out how to begin to make this happen. Below is some sample code that doesn't work but illustrates my goal. Any pointers anyone has would be much appreciated. I'm using R v2.9.0 on Windows with Hmisc v3.6-0 and maps v2.1-0. Cheers, eric library(Hmisc) library(maps) sample.data - data.frame(lat = c(12.1667, 14.6333, -6.874, 2.6167, 14.6833, 11.2, 3.2667, 11.4167, -13.8623, 13.1667), lon = c(-126.25, -103.4667, -88.4572, -93.65, -97.7, -88.65, -111.0167, -119.7333, -100.0748, -108.0333), exp.index = c(23.6266244576543, 2.06824648038330, 0, 1.46378849121688, 24.1824663424805, 0, 0.364600074527829, 4.468039274638, 0.543833744085446, 18.2301918845932)) xlim - c(-150, -80) ylim - c(-5, 30) print(xYplot(lat ~ lon, data = sample.data, size = sample.data$exp.index, xlim = xlim, ylim = ylim )) map(world, fill = TRUE, col = gray, xlim = xlim, ylim = ylim, add = TRUE) -- Eric Archer, Ph.D. Southwest Fisheries Science Center National Marine Fisheries Service North Torrey Pines Court La Jolla, CA 92037-1022 858-546-7121 (work) 858-546-7003 (FAX) ETP Cetacean Assessment Program: http://swfsc.noaa.gov/prd-etp.aspx Population ID Program: http://swfsc.noaa.gov/prd-popid.aspx Innocence about Science is the worst crime today. - Sir Charles Percy Snow Lighthouses are more helpful than churches. - Benjamin Franklin ...but I'll take a GPS over either one. - John C. Craig George __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.