Re: [R] rownames and plot lablels

On 4 Jan 2005 at 10:25, Derek Margetts wrote: I have a question about changing rownames. In the following function I am plotting the regression coeficients with their corresponding mean. Right now, the labels on the plot and the rownames in the dataframe are x1,x2,x3...etc. Is there a

[R] integer factorization

Hi has anyone coded up integer factorization? I want, for example, R factorize(60) $primes [1] 2 3 5 $powers [1] 2 1 1 (actually, I want the divisor function $\sigma_a(n)$, but coding this up requires integer factorization). -- Robin Hankin Uncertainty Analyst Southampton Oceanography Centre

Re: [R] rownames and plot lablels

It is sometimes important to know that row.names accesses the row names of a data frame, and rownames the first dimname of an array (including a matrix). They are almost equivalent, but not quite (e.g. row.names is generic and has methods for matrices and arrays). So the example would

[R] unlist kills R

When I try to unlist a very large list, R is killed without any other warning: A-as.list(as.data.frame(matrix(1:21639744,nrow=3578,ncol=6048))) with AA-unlist(A) or AA-c(A,recursive=TRUE) I get a R terminado (killed) and the end of the session. I think I'll need to get more RAM (now 1Gb, any

[R] Converting integers to chars i.e 1 to 01

Hello! I am producing a set of images and I would like them to be sorted by names I give. I was able to produce my names and add integer to them. That is easy. But my problem lies in sort of file from this process: figure_10.png figure_11.png figure_12.png ... figure_1.png figure_20.png ... So

Re: [R] warnings and errors with R CMD INSTALL

Hello, Am Mittwoch, den 05.01.2005, 06:47 + schrieb Prof Brian Ripley: On Wed, 5 Jan 2005, thomas wrote: But there is no package `pkg1' on CRAN. Try a real name like install.packages(tree) Well, of cause I didn't want install pkg1 or pkg2, the precise commandline was: 1. R

Re: [R] unlist kills R

Hi Manuel, try the following: A - data.frame(matrix(1:21639744, nrow=3578, ncol=6048)) AA - unlist(A, use.names=FALSE) I hope it helps. Best, Dimitris Dimitris Rizopoulos Ph.D. Student Biostatistical Centre School of Public Health Catholic University of Leuven Address: Kapucijnenvoer 35,

[R] make R package for windows on Linux

Hi, I made a package on a linux box. All worked fine. The package contains only R code (no C). I then wanted to make a zip file so that I could test the package on a windows machine. I have tried all the obvious ways to do this (and even some that are not!), but to no avail. The only

Re: [R] Converting integers to chars i.e 1 to 01

Hi Gregor, There still exist simple functions to achive that goal: Look at: x=1:111 formatC(format=d,x,flag=0,width=ceiling(log10(max(x [1] 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 [21] 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035

RE: [R] Converting integers to chars i.e 1 to 01

On 05-Jan-05 Gregor GORJANC wrote: Hello! I am producing a set of images and I would like them to be sorted by names I give. [...] So I would like to convert integers to something like 01 if upper limit for this conert is 10 or 001 for 100. [...] Hi Gregor, 'formatC' provides access to

Re: [R] Converting integers to chars i.e 1 to 01

? formatC Else (if you are linux) the following shell command can be useful... rename file_name_ file_name_0 file_name_[0-9]_bleh_*.png Where file_name_[0-9]_bleh_*.png is supposed to match all those files with a single digit, and the rename command adds a zero before that digit. rename can

[R] lme: error message with random=~1

Hello, I have an unbalanced mixed model design with two fixed effects site (2 levels) and timeOfDay (4 levels) and two random effects day (3 consecutive days) and trap (6 unique traps, 3 per site). The dependent variable is the body length (BL) of insect larvae from 7 to 29 individuals per trap

Re: [R] integer factorization

Hi Robin There is a function factorize() in the package conf.design library(conf.design) factorize(60) [1] 2 2 3 5 Hope this helps Christoph -- Christoph Buser [EMAIL PROTECTED] Seminar fuer Statistik, LEO C11 ETH (Federal Inst. Technology) 8092 Zurich SWITZERLAND phone: x-41-1-632-5414

Re: [R] Converting integers to chars i.e 1 to 01

Eric == Eric Lecoutre [EMAIL PROTECTED] on Wed, 05 Jan 2005 10:29:48 +0100 writes: Eric Hi Gregor, Eric There still exist simple functions to achive that goal: Eric Look at: x=1:111 formatC(format=d,x,flag=0,width=ceiling(log10(max(x Eric [1] 001 002 003 004

Re: [R] Converting integers to chars i.e 1 to 01

Gregor GORJANC wrote: Hello! I am producing a set of images and I would like them to be sorted by names I give. I was able to produce my names and add integer to them. That is easy. But my problem lies in sort of file from this process: figure_10.png figure_11.png figure_12.png ... figure_1.png

Re: [R] warnings and errors with R CMD INSTALL

thomas wrote: Hello, Am Mittwoch, den 05.01.2005, 06:47 + schrieb Prof Brian Ripley: On Wed, 5 Jan 2005, thomas wrote: But there is no package `pkg1' on CRAN. Try a real name like install.packages(tree) Well, of cause I didn't want install pkg1 or pkg2, the precise commandline was: 1. R CMD

Re: [R] lme: error message with random=~1

Hi Thomas, random=~1 works if your data frame is in groupedData format, check this: # Orthodont is in groupedData format fm1 - lme(distance~age+Sex, data=Orthodont, random=~1) # dat - as.data.frame(Orthodont) fm2.1 - lme(distance~age+Sex, data=dat, random=~1) `dat' is an ordinary data.frame

Re: [R] Converting integers to chars i.e 1 to 01

Thanks to all for valuable suggestions! -- Lep pozdrav / With regards, Gregor GORJANC --- University of Ljubljana Biotechnical Faculty URI: http://www.bfro.uni-lj.si Zootechnical Departmentmail: gregor.gorjanc at

[R] output from table() in matrix form

Hi How do I get the output from table() in matrix form? If I have R table(c(1,1,1,1,2,20)) 1 2 20 4 1 1 I want [,1] [,2] [,3] [1,]12 20 [2,]411 The problem is that names(table) is a vector of characters and I need the numeric values. I am using R

Re: [R] lme: error message with random=~1

Dimitris Rizopoulos wrote: Hi Thomas, random=~1 works if your data frame is in groupedData format, check this: # Orthodont is in groupedData format fm1 - lme(distance~age+Sex, data=Orthodont, random=~1) # dat - as.data.frame(Orthodont) fm2.1 - lme(distance~age+Sex, data=dat, random=~1) `dat'

Re: [R] output from table() in matrix form

Hi Robin, does this help: x - table(c(1,1,1,1,2,20)) matrix(c(as.numeric(names(x)), x), ncol=length(x), byrow=TRUE, dimnames=NULL) Best, Dimitris Dimitris Rizopoulos Ph.D. Student Biostatistical Centre School of Public Health Catholic University of Leuven Address: Kapucijnenvoer 35, Leuven,

Re: [R] output from table() in matrix form

__ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html

Re: [R] lme: error message with random=~1

Thomas Petzoldt wrote: Hello, I have an unbalanced mixed model design with two fixed effects site (2 levels) and timeOfDay (4 levels) and two random effects day (3 consecutive days) and trap (6 unique traps, 3 per site). The dependent variable is the body length (BL) of insect larvae from 7 to 29

RE: [R] output from table() in matrix form

You probably want something like: t1 - table( x ) t1 x 1 2 20 3 2 1 t2 - rbind( as.numeric( names( t1 ) ), t1 ) t2 1 2 20 1 2 20 t1 3 2 1 dimnames( t2 ) - NULL t2 [,1] [,2] [,3] [1,]12 20 [2,]321 Bendix -- Bendix Carstensen

Re: [R] lme: error message with random=~1

Hi Thomas, I don't quite understand what you want to do. If you use random=~1 (or random=~1|Subject if you don't have a groupedData), then you just fit a random-intercepts model. ranef(fm1) gives you the Empirical Bayes estimates (i.e., posterior means) for the random-effects which you can use

Re: [R] output from table() in matrix form

table works the way it does because it applies to *factors*, so the names are the factor levels of the argument after conversion. So if anything is wasteful, that is. How about using the guts of factor and table, via xx - unique(x) rbind(vals=xx, cnts=tabulate(match(x, xx))) ? On Wed, 5 Jan

Re: [R] lme: error message with random=~1

On Wed, 05 Jan 2005 13:31:51 +0100, Thomas Petzoldt [EMAIL PROTECTED] wrote: Dimitris Rizopoulos wrote: Hi Thomas, random=~1 works if your data frame is in groupedData format, check this: # Orthodont is in groupedData format fm1 - lme(distance~age+Sex, data=Orthodont, random=~1)

Re: [R] output from table() in matrix form

On Jan 5, 2005, at 12:59 pm, Prof Brian Ripley wrote: table works the way it does because it applies to *factors*, so the names are the factor levels of the argument after conversion. So if anything is wasteful, that is. How about using the guts of factor and table, via xx - unique(x)

[R] hist.POSIXt filled bars - axis color changes

Hi all, I'm plotting a histogram of dates and would like to shade the bars, e.g. hist(.leap.seconds,years,col='gray',freq=T) -but the axis color also changes, how do I prevent that? thx in advance Janus [[alternative HTML version deleted]]

Re: [R] make R package for windows on Linux

On Wed, 2005-01-05 at 09:34 +, Halldor Bjrnsson wrote: Hi, I made a package on a linux box. All worked fine. The package contains only R code (no C). I then wanted to make a zip file so that I could test the package on a windows machine. I have tried all the obvious ways to do this (and

[R] Replacing all NA values in a matrix

OK, dumb question, and it is probably in the docs somewhere, but after 12 months working with R and quite a while looking at the docs, I still don't know (or have forgotten) how to replace all NA values in a matrix at once with some other value. I can do it column by column using is.na(), but I

Re: [R] make R package for windows on Linux

Hi I do it for the geoR package following the excelent and detailed instructions provided by Yan and Rossini: Building Microsoft Windows Versions of R and R packages under Intel Linux available at the Contributed Documentation in the R web-site Notice that not having C/Fortran/C++ code make

Re: [R] Replacing all NA values in a matrix

You have it already h - matrix(rnorm(100),nrow=20) h [,1] [,2][,3] [,4] [,5] [1,] 0.4669801 0.3349176 -1.60686041 0.981491440 0.1627222 [2,] -0.2580262 -0.2620413 0.53852801 1.294129626 -0.1632906 [3,] 0.9654591 1.0077212 -0.45603772

RE: [R] Replacing all NA values in a matrix

x - matrix(rnorm(100),ncol=10) x[x0] - NA x[is.na(x)] - 1000 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of michael watson (IAH-C) Sent: Wednesday, January 05, 2005 9:26 AM To: R-help@stat.math.ethz.ch Subject: [R] Replacing all NA values in a

RE: [R] Replacing all NA values in a matrix

Doh, replace() does the job just fine. Sheesh, I'm not coping well with work post christmas ;-) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of michael watson (IAH-C) Sent: 05 January 2005 14:26 To: R-help@stat.math.ethz.ch Subject: [R] Replacing all NA

RE: [R] make R package for windows on Linux

From: Marc Schwartz On Wed, 2005-01-05 at 09:34 +, Halldor Björnsson wrote: Hi, I made a package on a linux box. All worked fine. The package contains only R code (no C). I then wanted to make a zip file so that I could test the package on a windows machine. I have tried

AW: [R] Replacing all NA values in a matrix

Replacing the NA´s with eg. 1 : a 1 2 3 4 1 20 50 10 80 2 NA 19 NA 49 3 NA 32 NA 61 4 45 101 44 190 a[try(is.na(a)) == TRUE] - 1 a 1 2 3 4 1 20 50 10 80 2 1 19 1 49 3 1 32 1 61 4 45 101 44 190 I this can help you, Matthias -Ursprüngliche Nachricht-

RE: [R] Replacing all NA values in a matrix

What you should keep in mind is that a matrix in R is nothing more than a vector (formed by stacking the columns of the matrix) with the dim attribute. Thus you can do what you want to do by treating the matrix as a vector; e.g., mymat[is.na(mymat)] - myFavoriteValue HTH, Andy From: michael

Re: [R] Replacing all NA values in a matrix

Hi Michael, try this: mat - matrix(1:25, 5, 5) mat[sample(25, 10)] - NA mat # mat[is.na(mat)] - 100 mat I hope it helps. Best, Dimitris Dimitris Rizopoulos Ph.D. Student Biostatistical Centre School of Public Health Catholic University of Leuven Address: Kapucijnenvoer 35, Leuven, Belgium

RE: [R] integer factorization

See also primeFactors() and allFactors(): http://www.maths.lth.se/help/R/.R/library/R.basic/html/primeFactors.html http://www.maths.lth.se/help/R/.R/library/R.basic/html/allFactors.html in the R.basic package part of the R.classes bundle: http://www.maths.lth.se/help/R/R.classes/ Cheers

Re: [R] Replacing all NA values in a matrix

michael watson (IAH-C) wrote: OK, dumb question, and it is probably in the docs somewhere, but after 12 months working with R and quite a while looking at the docs, I still don't know (or have forgotten) how to replace all NA values in a matrix at once with some other value. I can do it column by

RE: [R] Replacing all NA values in a matrix

Dear Michael, A[is.na(A)] - value I hope this helps, John John Fox Department of Sociology McMaster University Hamilton, Ontario Canada L8S 4M4 905-525-9140x23604 http://socserv.mcmaster.ca/jfox -Original Message-

Re: [R] hist.POSIXt filled bars - axis color changes

Janus Larsen wrote: Hi all, I'm plotting a histogram of dates and would like to shade the bars, e.g. hist(.leap.seconds,years,col='gray',freq=T) -but the axis color also changes, how do I prevent that? Looks like that's not very easy with the current implementation, see the code in

RE: [R] Replacing all NA values in a matrix

Michael -- is.na works on the full matrix. The commands below construct a matrix, insert some NA's, and then convert them all to 0. temp1 - matrix(runif(25), 5, 5) temp1[temp1 0.1] - NA temp1[is.na(temp1)] - 0 Hope this helps. Regards, Matt Wiener -Original Message- From:

Re: [R] lme: error message with random=~1

Douglas Bates wrote: I'm not sure what model you want to fit here. To specify a random effect in lme you need both a grouping factor and a model matrix. The error message indicates that lme is unable to determine a grouping factor. It would be correct syntax if you added a single level

[R] count element in column

Hi, I 've a matrix n*1 (thus a column) and I would like to count the number of negative element inside. Can you help me? Thanks! eg: res[,1]= 1 -3 -1 How obtain the number 2 (number of negative-element)? __

[R] variance of combinations of means - off topic

Hello, and please excuse this off-topic question, but I have not been able to find an answer elsewhere. Consider a value Z that is calculated using the product (or ratio) of two means X_mean and Y_mean: Z=X_mean*Y_mean. More generally, Z=f(X_mean, Y_mean). The standard error of Z will be a

[R] lme, glmmPQL, multiple random effects

Hi all - R2.0.1, OS X Perhaps while there is some discussion of lme going on. I am trying to execute a glmm using glmmPQL from the MASS libray, using the example data set from McCullagh and Nelder's (1989, p442) table 14.4 (it happens to be the glmm example for GENSTAT as well). The data

Re: [R] lme: error message with random=~1

Thomas Petzoldt wrote: Douglas Bates wrote: I'm not sure what model you want to fit here. To specify a random effect in lme you need both a grouping factor and a model matrix. The error message indicates that lme is unable to determine a grouping factor. It would be correct syntax if you

Re: [R] integer factorization

ChrBu == Christoph Buser [EMAIL PROTECTED] on Wed, 5 Jan 2005 11:13:30 +0100 writes: ChrBu Hi Robin ChrBu There is a function factorize() in the package conf.design ChrBu library(conf.design) ChrBu factorize(60) ChrBu [1] 2 2 3 5 yes, as quick search on Jonathan

[R] (no subject)

Hi, I'm trying to use the version of dchip combined with R to analyze my data. I need R version 1.6 which fits for dchip as dchip manual said. So I would appreciate a lot if someone could tell me where I could find this version and download? I'm using Windows 2000. Thanks, Jean Qun(Jean) Shi

RE: [R] count element in column

How about this? length(res[res 0, 1]) HTH, Andy -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Frederic renaud Sent: Wednesday, January 05, 2005 11:08 AM To: r-help@stat.math.ethz.ch Subject: [R] count element in column Hi, I 've a matrix n*1

Re: [R] count element in column

How about sum(res0)? -- [EMAIL PROTECTED] The computer should be doing the hard work. That's what it's paid to do, after all. -- Larry Wall in [EMAIL PROTECTED] It is rumored that on Wed, 5 Jan 2005 08:07:34 -0800 (PST) Frederic renaud [EMAIL PROTECTED] wrote: Hi, I

Re: [R] count element in column

How about sum(res0)? -- [EMAIL PROTECTED] The computer should be doing the hard work. That's what it's paid to do, after all. -- Larry Wall in [EMAIL PROTECTED] It is rumored that on Wed, 5 Jan 2005 08:07:34 -0800 (PST) Frederic renaud [EMAIL PROTECTED] wrote: Hi, I

RE: [R] variance of combinations of means - off topic

You could try googling for delta method. I believe MASS even has code for that... Andy From: Bill Shipley Hello, and please excuse this off-topic question, but I have not been able to find an answer elsewhere. Consider a value Z that is calculated using the product (or ratio) of two

RE: [R] count element in column

How about this? length(res[res 0, 1]) HTH, Andy or simply sum(res0) . For R beginners: This works because the logical res0 vector is automatically coerced to a numeric vector of 0's and 1's by sum(). -- Bert Gunter Genentech Non-Clinical Statistics South San Francisco, CA

[R] Targeting the elements that satisfy matching rules excluding the NA

Dear R-List, here my problem: a - c(gio,gao,geo,NA,1,alpha) b - 1:6 data.frame(V1=a,V2=b) - c c V1 V2 1 gio 1 2 gao 2 3 geo 3 4 NA 4 5 1 5 6 alpha 6 rownames(c) %in% grep(a,as.character(c$V1)) [1] FALSE TRUE FALSE FALSE FALSE TRUE while I would like to obtain [1]

Re: [R] count element in column

x-c(-3. -4.7, -.005, 1, 9) length(x[x0]) [1] 3 Anne - Original Message - From: Frederic renaud [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Sent: Wednesday, January 05, 2005 5:07 PM Subject: [R] count element in column Hi, I 've a matrix n*1 (thus a column) and I would like to

Re: [R] variance of combinations of means - off topic

I know two standard ways to approach this. The traditional approximation is called the delta method; it uses a Taylor series approximation, usually of first order but could be higher. Googling for delta method produced several useful hits just now. The second method is Monte Carlo.

[R] matrix no longer is array in 2.0.1?

I have an S4 class which extends array and has other slots, and in upgrading to 2.0.1 (from 1.9.1) I have encountered a change in behaviour. This causes me some difficulties if I want to allow 2-dimensional arrays in the slot (which I do). The following (in 2.0.1) illustrates the point:

[R] shape parameter in Lindsay's gnlr

Dear all I'm using Jim Lindsay's glnr to perform some maximum likelihood fitting. What I would like to know is to what does the shape parameter returned correspond to when using the Laplace distribution and the Cauchy distribution? In particular, given a Laplace distrib 1/(2*s)

Re: [R] Tuning string matching

On Wed, 5 Jan 2005 [EMAIL PROTECTED] wrote: Dear list, I spent about two hours searching on the message archive, with no avail. I have a list of people that have to pass an on-line test, but only a fraction of them do it. Moreover, as they input their names, the resulting string do not always

Re: [R] variance of combinations of means - off topic

Hi, Andy: MASS4 has section 5.7 Bootstrap and Permutation Methods. Is this what you are suggesting? It certainly is relevant to the question (but not to the delta method, except as a means of checking on it). Thanks, spencer graves Liaw, Andy wrote: You could try googling

[R] plotting percent of incidents within different 'bins'

Hi Say I have some data, two columns in a table being a binary outcome plus a predictor and I want to plot a graph that shows the percentage positives of the binary outcome within bands of the predictor, e.g. Outcome predictor 0 1 1 2 1

RE: [R] Tuning string matching

It sounds like what you want is a rudimentary spell-checker whose word is the input name, and whose dictionary is an array of your database names. Spell checking rules are designed to find missing repeats, transposed letters, extra letters... precisely the reasons you're not matching your names to

RE: [R] variance of combinations of means - off topic

What I have in mind is the discussion on pp. 167-172 of `S Programming'. Cheers, Andy From: Spencer Graves Hi, Andy: MASS4 has section 5.7 Bootstrap and Permutation Methods. Is this what you are suggesting? It certainly is relevant to the question (but not to the delta

RE: [R] Tuning string matching

This is a rather complex problem. I'm not aware of an R function / package that can do something like this, but in case you need to build it from scratch read http://support.sas.com/documentation/periodicals/obs/obswww15/index.html If you're familiar with SAS you could translate the code to R.

[R] find parameters for a gamma distribution

hello, i have just started exploring R as an alternative to matlab for data analysis. so +far everything is _very_ promising. i have a question though regarding parameter +estimation. i have some data which, from a histogram plot, appears to arise from +a gamma distribution. i gather that you

Re: [R] Targeting the elements that satisfy matching rules excluding the NA

Giovanni Malerba bobo at medgen.univr.it writes: : : Dear R-List, : here my problem: : a - c(gio,gao,geo,NA,1,alpha) : b - 1:6 : data.frame(V1=a,V2=b) - c : c : V1 V2 : 1 gio 1 : 2 gao 2 : 3 geo 3 : 4 NA 4 : 5 1 5 : 6 alpha 6 : : rownames(c) %in%

[R] fSeries library

Hi, I am trying to use fSeries library form CRAN, especialy the armaFit function. armaFit(formula = x ~ arima(2, 0, 1), method = c(CSS-ML, ML, CSS, yw, burg, ols, mle), include.mean = TRUE, fixed = NULL, fracdiff.M = 100, fracdiff.h = -1, title = , description = , ...) The problem that I

[R] Course***R/S-plus Fundamentals and Programming Techniques @ 4 locations, January 2005

Happy New Year! XLSolutions Corporation (www.xlsolutions-corp.com) is proud to announce 2-day R/S-plus Fundamentals and Programming Techniques. Chicago, IL January 13th-14th, 2005 San Francisco, CA -- January 13th-14th, 2005

RE: [R] plotting percent of incidents within different 'bins'

You want: tapply( Outcome, predictor, mean ) Bendix Carstensen -- Bendix Carstensen Senior Statistician Steno Diabetes Center Niels Steensens Vej 2 DK-2820 Gentofte Denmark tel: +45 44 43 87 38 mob: +45 30 75 87 38 fax: +45 44 43 07 06 [EMAIL PROTECTED] www.biostat.ku.dk/~bxc

Re: [R] Tuning string matching

Sorry for joining late, but I wanted to see if my search page could help. (I don't know which search archive you looked at.) I entered fuzzy string match* and got a few things that look relevant, including the agrep function. As for the second part of the question, that seems to be a coding

RE: [R] (no subject)

Hi Andy, Thanks a lot for your promptly response. I searched the whole web site, I found the source code for version 1.6.X. Since I'm not a computer person, I don't how to compile it, but what I want is binary file for Windows 2000 so that I could continue to work on my data. Could you or someone

Re: [R] plotting percent of incidents within different 'bins'

You can use 'cut' to create the breaks.. Actually there are 8 in the 3-4 range: Outcome predictor 10 1 21 2 31 2 40 3 50 3 60 2 71 3 81 4 91 4 10

[R] strange behaviour of negative binomial

Dear list, I ran into a strange behaviour of the pnbinom function - or maybe I just made a stupid mistake. First thing is that pnbinom seems to be very slow. The other - more interesting one - is that I get two different curves when I plot the estimated density and the density given by pnbinom.

[R] cubic spline smoother with heterogeneous variance.

Hello. I want to estimate the predicted values and standard errors of Y=f(t) and its first derivative at each unique value of t using the smooth.spline function. However, the data (plant growth as a function of time) show substantial heterogeneity of variance since the variance of plant mass

Re: [R] find parameters for a gamma distribution

Andrew Collier [EMAIL PROTECTED] writes: hello, i have just started exploring R as an alternative to matlab for data analysis. so +far everything is _very_ promising. i have a question though regarding parameter +estimation. i have some data which, from a histogram plot, appears to

Re: [R] find parameters for a gamma distribution

You want: library(MASS) ?fitdist cheers Brett Brett Melbourne, Postdoctoral Fellow Biological Invasions IGERT www.cpb.ucdavis.edu/bioinv Center for Population Biology University of California Davis CA 95616 - Original Message - From: Andrew Collier [EMAIL PROTECTED] To:

Re: [R] find parameters for a gamma distribution

First, you want to fit the data not the histogram counts (binned data). Second, glm does not do a very principled fit of a gamma (it is a moment estimator). Something like d - rgamma(1000, 20, scale = 2) summary(glm(d ~ 1, Gamma)) Coefficients: Estimate Std. Error t value Pr(|t|)

Re: [R] find parameters for a gamma distribution

Actually, that should be: library(MASS) ?fitdistr You want: library(MASS) ?fitdist cheers Brett Brett Melbourne, Postdoctoral Fellow Biological Invasions IGERT www.cpb.ucdavis.edu/bioinv Center for Population Biology University of California Davis CA 95616 - Original Message - From:

Re: [R] (no subject)

Qun Shi [EMAIL PROTECTED] writes: Hi Andy, Thanks a lot for your promptly response. I searched the whole web site, I found the source code for version 1.6.X. Since I'm not a computer person, I don't how to compile it, but what I want is binary file for Windows 2000 so that I could continue

Re: [R] strange behaviour of negative binomial

On Wed, 5 Jan 2005, dax42 wrote: Dear list, I ran into a strange behaviour of the pnbinom function - or maybe I just made a stupid mistake. First thing is that pnbinom seems to be very slow. The other - more interesting one - is that I get two different curves when I plot the estimated density

Re: [R] find parameters for a gamma distribution

On Wed, 5 Jan 2005, Prof Brian Ripley wrote: First, you want to fit the data not the histogram counts (binned data). Second, glm does not do a very principled fit of a gamma (it is a moment estimator). Something like d - rgamma(1000, 20, scale = 2) summary(glm(d ~ 1, Gamma)) Coefficients:

RE: [R] (no subject)

Googling for `rw1061.exe' turned up: http://www.cipic.ucdavis.edu/~dmrocke/Class/EAD289D/R/rw1061.exe Andy From: Qun Shi Hi Andy, Thanks a lot for your promptly response. I searched the whole web site, I found the source code for version 1.6.X. Since I'm not a computer person, I

Re: [R] strange behaviour of negative binomial

dax42 [EMAIL PROTECTED] writes: Dear list, I ran into a strange behaviour of the pnbinom function - or maybe I just made a stupid mistake. First thing is that pnbinom seems to be very slow. The other - more interesting one - is that I get two different curves when I plot the estimated

Re: [R] strange behaviour of negative binomial

dax42 Dax42 at web.de writes: : : Dear list, : : I ran into a strange behaviour of the pnbinom function - or maybe I : just made a stupid mistake. : First thing is that pnbinom seems to be very slow. The other - more : interesting one - is that I get two different curves when I plot the :

[R] Rcmd check Error help

R-help, I'm the primary developer for an increasingly large R package with over three thousand lines of code. Unfortunately, do the complexity of the code, I sometimes am required to change several interoperating parts of the package before testing for bugs and performance. And sometimes unnoticed

[R] Using the Rprofile file to automatically plot data on Startup of R version 2.0.1.

Dear R Help Members, I have some R functions that plot semiconductor data. I would like to automate these plots for individuals in our group such that they don't have to know R. I have read the R help manuals and postings but have not found this problem. I am using R version 2.0.1 under a

Re: [R] strange behaviour of negative binomial

Hi, I am sorry for the incorrect terms. Of course I mean the cumulative distribution functions. As I just got two answers telling me my problem does not exist, I tried again on a different setup - and indeed it works. So, my first run was done on a Mac OS X 10.3.7 running R 2.0.0, GUI version.

Re: [R] find parameters for a gamma distribution

Andrew Collier wrote: hello, i have just started exploring R as an alternative to matlab for data analysis. so +far everything is _very_ promising. i have a question though regarding parameter +estimation. i have some data which, from a histogram plot, appears to arise from +a gamma

Re: [R] find parameters for a gamma distribution

Andrew Collier wrote: hello, i have just started exploring R as an alternative to matlab for data analysis. so +far everything is _very_ promising. i have a question though regarding parameter +estimation. i have some data which, from a histogram plot, appears to arise from +a gamma

Re: [R] find parameters for a gamma distribution

The help page of ?dgamma says: The mean and variance are E(X) = a*s and Var(X) = a*s^2. So, to estimate the parameters in your example, try the following: d - rgamma(10, 20, scale = 2) var(d)/mean(d) [1] 1.992091 mean(d)^2/var(d) [1] 20.09559 ... you may use these as start values for

Re: [R] variance of combinations of means - off topic

Liaw, Andy wrote: You could try googling for delta method. I believe MASS even has code for that... Andy If you have the original data you can bootstrap --- else you need the standar errors and correlation between the means, and can use the delta methos as above. You could even use D or

[R] RSvgDevice stroke question

I had a quick question on the RSvgDevice package if there are any users out there. I perused the archives and the docs and didn't see anything, maybe I missed? I have created simple boxplots via devSVG() in both Windoze and Linux and it seems that there is an attribute difference in that the

[R] fSeries

Hi! For the person who asked about the armaFit from the fSeries library, here is an example: library(its) x1 - priceIts(instrument = c(^ftse), start = 1998-01-01, + quote = Close) fit - armaFit(x1 ~ arima(1,1,1)) fit Call: armaFit(formula = x1 ~ arima(1, 1,

Re: [R] Rcmd check Error help

McGehee, Robert Robert.McGehee at geodecapital.com writes: : : R-help, : I'm the primary developer for an increasingly large R package with over : three thousand lines of code. Unfortunately, do the complexity of the : code, I sometimes am required to change several interoperating parts of : the

RE: [R] Using the Rprofile file to automatically plot data on Sta rtup of R version 2.0.1.

Dear John, I belive your problem has to do with the sequence of startup. I think that .Rprofile is called before the required libraries are attached. You might like to try putting your code into a .First() function and run it that way. Cheers, Andreas Dr Andreas Kiermeier Statistician SARDI

Re: [R] strange behaviour of negative binomial

I tried it on Windows XP under both 2.0.1 and 2.1.0 and it seemed to work both times. I issued the command: set.seed(1) before both runs to ensure that I was actually using the same random numbers. I suggest you try that in all your runs too just in case its a problem with some sets of

[R] multiple trees

Hi, there: I made a function to do k-fold cross-validation as below. Basically whenever I call cv(test) for example, an error message like: 20Fold 1 Error in model.frame(formula, rownames, variables, varnames, extras, extranames, : variable lengths differ please help. My test

  1   2   >