[R] Combined grouped and stacked bargraph
Dear R-list I am having some trouble drawing a bar-graph with two groups, both of which are stacked. Here are my data in the dput format: cs.not.log.bp - ( structure(c(168, 69, 16, 69, 41, 6, 148, 6, 5, 4, 7, 4, 4, 2, 7, 2, 4, 2, 4, 2, 1, 0, 2, 0), .Dim = c(4L, 6L), .Dimnames = list( c(IUCN.Terrestrial, IUCN.Marine, National.CS.Terrestrial, National.CS.Marine), c(NE, LC, NT, VU, EN, CR ))) ) The database format is shown below, where columns represent conservation status and the rows are two classification methods each split into marine and terrestrial: NE LC NT VU EN CR IUCN.Terrestrial168 41 5 4 4 1 IUCN.Marine 69 6 4 2 2 0 National.CS.Terrestrial 16 148 7 7 4 2 National.CS.Marine 69 6 4 2 2 0 I would like to plot the conservation status according to two classifications (i.e. my groups - IUCN status and national status), and for each of those groups I would like data for the marine and terrestrial species to be stacked. I have tried the following code (where cs.not.log.bp is my data), but it does not work: barplot(cs.not.log.bp[c(1:2),], xlab = Conservation status, ylab = Number of species, col = c(grey90,grey80), ylim = c(0,250), space = 2) barplot(cs.not.log.bp[c(3:4),], col = c(grey60,grey30), beside = T,add = T,names.arg = NA) legend(topright,c(IUCN Terrestrial,IUCN Marine,National CS Terrestrial,National CS Marine), col = c(grey90,grey80,grey60,grey30), pch = 15) What happens is that some of the data in the second group stacks onto the first group and then the remainder forms a second group. I would like only like data (i.e. from the same database row) to stack within a group. There was one other similar post on the R-list (http://r.789695.n4.nabble.com/barplot-question-td3670861.html ) where the user had the same problem as I did, but it does not seem that this was resolved. Please let me know if you have any suggestions. Thanks and best wishes, Nicola This e-mail communication and any attachments are confidential and are intended only for the individual(s) or entity named above and others who have been specifically authorized to receive it. If you are not the intended recipient, please do not copy, use or disclose the contents of this communication to others. Please notify the sender that you have received this email in error by replying to the e-mail or by telephoning the sender. Please then delete the e-mail and any copies of it. This information may contain private, confidential or privileged material. Thank you. [[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 can I read the text or character string from a txt file?
Hello, I have a large number of time series, which needs to be transformed by log or difference. Some of them are just processed by level (LV) without any transformation. For that purpose, I produce a text file (.csv or .xls) as follows: DLN DLNDLN LV LV LV... How can I read the preceding strings so that I can easily access them, i.e., S[1]=DLN, S[2]=DLN, S[3]=DLN, S[4]=LV,S[5]=LV,S[6]=LV? I tried read.csv and read.table, but they don't work well. If I can access the string, then I will be able to write an if statement so that If the string is DLN, then take log and then difference. If the string is LV, then just keep it as it is. Thanks, miao [[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] Hmisc's latex: na.blank and grouping not working as expected
Dear expeRts, Why does na.blank=TRUE not replace the NA's in the following LaTeX table? x - matrix(1:72, ncol=4, nrow=8) colnames(x) - c(gr1.sgr1, gr1.sgr2, gr2.sgr1, gr2.sgr2) rn - apply(expand.grid(beta=c(0.25, 0.75), n=c(100, 500), d=c(10, 100))[, 3:1], 2, rmNames) x - cbind(rn, x) # append columns containing the row labels x[2,5] - NA stopifnot(is.na(x[2,5])) require(Hmisc) latex(x, file=, na.blank=TRUE, rowlabel=c(d, n, beta), booktabs=TRUE) In the end, I would like to have the columns displayed in groups like this: Group 1 Group 2 d n beta Sub-group 1 Sub-group 2 Sub-group 1 Sub-group 2 10 100 0.25 1 9 0.75 2 500 0.25 310 0.75 411 ... ... 100 100 0.25 512 0.75 613 500 0.25 7... 0.75 8 If anybody knows how to do this, please let me know :-) This is (one of) my trial(s): latex(x, file=, cgroup=c(, Group 1, Group 2), n.cgroup=c(3, 2, 2), na.blank=TRUE, rowlabel=c(d, n, beta), booktabs=TRUE) Why are there two empty columns inserted and the table has suddenly 9 columns instead of 7? Cheers, Marius __ 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] Define lower-upper bound for parameters in Optim using Nelder-Mead method
Ben Bolker bbolker at gmail.com writes: Ted.Harding at wlandres.net writes: In addition to these options, there is also a derivative-free box-constrained optimizer (bobyqa) in the 'minqa' package (and in an optim-like wrapper via the optimx package), and a box-constrained Nelder-Mead optimizer in the development (r-forge) version of lme4, which is based on the NLopt optimization library (also accessible via the nloptr package). I could add another Nelder-Mead implementation in package 'dfoptim'. It comes in pure R and is still quite efficient, based on Kelley's well-known book code. It exists in unconstrained and box-constraint versions. The optimization world in R is by now really scattered across many different package with sometimes 'strange' names. Some of the packages have not yet made it from R-Forge to CRAN. Unfortunately, the Optimization task view is not of much help anymore in this shattered world. We will get a lot more of these questions on R-help if we do not come up with a solution to this problem, for instance more up-to-date optimization functions in R base, a recommened package for optimization, or e.g. an optimization guide as a kind of global vignette. Hans Werner __ 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 in poLCA
Hi My data looks like this dat= X1 X2 Group 84 44 1 86 29 1 94 77 1 78 87 2 94 78 2 60 31 2 I use the formula form = cbind(X1,X2) ~ Group poLCA(form,dat) But i'm getting error stating that ALERT: some manifest variables contain values that are not positive integers. For poLCA to run, please recode categorical outcome variables to increment from 1 to the maximum number of outcome categories for each variable Please can any one help - Thanks in Advance Arun -- View this message in context: http://r.789695.n4.nabble.com/Help-in-poLCA-tp4602300.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] calibration of Garch models to historical data
I have done the usual estimation of GARCH models, applied to my historical dataset (commodities futures) with a maximum likelihood function and selected the best model on the basis of information criteria such as Akaike and Bayes. Can somebody explain me please the calibration scheme for a GARCH model? I was not able to find a paper, dealing with exactly this algorithm for my case. I only understood that I have to compare the performance of the best GARCH model (from the estimation step), fitted to my historical dataset and a GARCH simulation (let's abbreviate this Squared Error difference to E2). However, it is not clear to me: - with what parameters' values to start this simulation, - how many times it is normal to perform it, and - what to compare via E2 (maximum likelihood values, or parameter values) - how to constructassess E2 for the GARCH case. Thank you in advance for your suggestions. Ivette -- View this message in context: http://r.789695.n4.nabble.com/calibration-of-Garch-models-to-historical-data-tp4602606.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] How to read ANOVA output
Hey all who have responded to this post. I am a newbie to ANOVA analysis in R, and let me tell you- resources for us learners are scant, horrible, unclear, imprecise.. in other words.. the worst ever. So advice like go look it up in your classical textbook or on google is not helpful at all. I am scouring posts like these to try to find some kind soul who not only understands the basics, but is willing to help us new folk out.. sadly.. here is not the place. -- View this message in context: http://r.789695.n4.nabble.com/How-to-read-ANOVA-output-tp2329457p4602403.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] DepmixS4
Hi I am trying to use depmixS4 package. Based on the documentation, it seems that depmix allows one to fit an HMM model based on a training data with time-varying co-variates. However, I did not find any routines which can help test the accuracy on the fitted HMM model on out-of-sample data. Can someone confirm if that is indeed the case? Also are there any alternate packages for the same? Thanks -Deepak -- View this message in context: http://r.789695.n4.nabble.com/DepmixS4-tp4602417.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] Tutorial for ff package
Is anybody planning to write an extensive tutorial on the ff package? I am finding the web links highly inadequate. Regards, Indrajit [[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] Referencing factors through their equivalent numeric level
Hey folks I'm sorry for bringing what must be a very simple question to R-help, but after some research I haven't been able to find a solution to my problem. Suppose I create a simple factor: [code] x-c(A,B,B,C,A) x [1] A B B C A x - as.factor(x) x [1] A B B C A Levels: A B C [/code] Now, when I see this factor in terms of its numeric level values, I get [code] as.numeric(x) [1] 1 2 2 3 1 [/code] Suppose I have [code] y - 2 [/code] I want the numeric value of y to reference the level of factor x. That is, I am looking for a function (`foo') so that I will get the following [code] foo(y) #or maybe foo(y,x) [1] B [/code] I can think of a roundabout way of doing through a user defined function, but I am sure that there is a built-in function that offers this functionality. I'd be grateful if someone could tell me what that function is. Thanks in advance -- Kaushik Krishnan (kaushik.s.krish...@gmail.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] list objects calculation
I have two kinds of list, for example, one is like t[[1]]= 1 6 2 7 3 8 4 9 5 10 ... t[[731]] the other is k[[1]]= 9 10 ... k[[731]] I want to have a new list,like x x[[1]]= (1-9)/9(6-10)/10 (2-9)/9(7-10)/10 (3-9)/9(8-10)/10 (4-9)/9(9-10)/10 (5-9)/9(10-10)/10 ... x[[731]] How should I do? Thank you. -- View this message in context: http://r.789695.n4.nabble.com/list-objects-calculation-tp4602437.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] Extracting results from a median polish
Quick question from a new user to R, How do I extract my solution of a median polish matrix from R to a spreadsheet file such as .csv? From my reading of my guide book (R for SPSS and SAS users version 2), I deduce that exporting a file to .csv would look like the following: write.csv(medpolish, file =outfilename.csv, row.names = FALSE) , by I get the following: Error in as.data.frame.default(x[[i]], optional = TRUE) : cannot coerce class 'function' into a data.frame So far I've been copy/pasting segment by segment into Excel and running text2column, but there has got to be a better way. Martin R. Lefebvre [[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] Numeric data not numeric in .csv file
On 05/02/2012 10:47 AM, Eve Proper wrote: I am a raw novice to R, playing around with a mini .csv dataset created in Excel. I can read it in and the data looks OK in Excel and upon initial inspection in R: hikes- read.csv(/Users/eproper/Desktop/hikes.csv, header=TRUE) print(hikes) does exactly what it is supposed to do. Two of the variables are genuine strings, but the others ought to be numeric, and R will calculate their min, max etc. However, is.numeric returns FALSE for all of them; storage.mode returns language. as.numeric returns Error: 'pairlist' object cannot be coerced to type 'double'. In what I suspect is a related problem, any command that calls for a variable name requires an initial ~ to work. That is, instead of plot(miles) I have to use plot(~miles). No doubt there is some very elementary mistake I am making, but I can't figure it out. Any help would be appreciated. Hi Eve, Have you tried as.numeric on them? As Jeff suggested, you may be importing spaces along with the digits or some other character that changes the class of the variable. Also note that the default behavior of functions like read.csv is to coerce all of the values in a column of the resulting data frame to the lowest common denominator. If you have one text value in a column of numbers, you usually get factor values. This is due to the restriction that all values in a column must be of the same class (data type). Jim __ 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 plot stacked histogram in R?
Hi, I am working on data analysis. I need to plot stacked histogram for two Files. File1: 1 2 3 3 4 4 File2: 4 5 6 6 7 7 7 How can i plot them on same graph? Thanks -- View this message in context: http://r.789695.n4.nabble.com/How-to-plot-stacked-histogram-in-R-tp4602369.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] Batch importing data
Thank you very much. -- View this message in context: http://r.789695.n4.nabble.com/Batch-importing-data-tp4592997p4602378.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] Combined grouped and stacked bargraph
On 05/02/2012 04:18 PM, Nicola Van Wilgen wrote: Dear R-list I am having some trouble drawing a bar-graph with two groups, both of which are stacked. Here are my data in the dput format: cs.not.log.bp- ( structure(c(168, 69, 16, 69, 41, 6, 148, 6, 5, 4, 7, 4, 4, 2, 7, 2, 4, 2, 4, 2, 1, 0, 2, 0), .Dim = c(4L, 6L), .Dimnames = list( c(IUCN.Terrestrial, IUCN.Marine, National.CS.Terrestrial, National.CS.Marine), c(NE, LC, NT, VU, EN, CR ))) ) The database format is shown below, where columns represent conservation status and the rows are two classification methods each split into marine and terrestrial: NE LC NT VU EN CR IUCN.Terrestrial168 41 5 4 4 1 IUCN.Marine 69 6 4 2 2 0 National.CS.Terrestrial 16 148 7 7 4 2 National.CS.Marine 69 6 4 2 2 0 I would like to plot the conservation status according to two classifications (i.e. my groups - IUCN status and national status), and for each of those groups I would like data for the marine and terrestrial species to be stacked. I have tried the following code (where cs.not.log.bp is my data), but it does not work: barplot(cs.not.log.bp[c(1:2),], xlab = Conservation status, ylab = Number of species, col = c(grey90,grey80), ylim = c(0,250), space = 2) barplot(cs.not.log.bp[c(3:4),], col = c(grey60,grey30), beside = T,add = T,names.arg = NA) legend(topright,c(IUCN Terrestrial,IUCN Marine,National CS Terrestrial,National CS Marine), col = c(grey90,grey80,grey60,grey30), pch = 15) What happens is that some of the data in the second group stacks onto the first group and then the remainder forms a second group. I would like only like data (i.e. from the same database row) to stack within a group. There was one other similar post on the R-list (http://r.789695.n4.nabble.com/barplot-question-td3670861.html ) where the user had the same problem as I did, but it does not seem that this was resolved. Hi Nicola, This is somewhat unusual. You can do a QD like this: barstack-function(x,y,heights,width,border=par(fg),col=NA) { nrect-length(heights) rect(rep(x-width/2,nrect),c(0,cumsum(heights[1:(nrect-1)])), rep(x+width/2,nrect),cumsum(heights),border=border,col=col) } cs.not.log.bp - (structure(c(168, 69, 16, 69, 41, 6, 148, 6, 5, 4, 7, 4, 4, 2, 7, 2, 4, 2, 4, 2, 1, 0, 2, 0), .Dim = c(4L, 6L), .Dimnames = list( c(IUCN.Terrestrial, IUCN.Marine, National.CS.Terrestrial, National.CS.Marine), c(NE, LC, NT, VU, EN, CR plot(0,xlim=c(0.5,6.5),ylim=c(0,240),type=n) for(stack in 1:6) { barstack(stack-0.2,0,cs.not.log.bp[1:2,stack],0.4, col=c(lightblue,blue)) barstack(stack+0.2,0,cs.not.log.bp[3:4,stack],0.4, col=c(lightgreen,green)) } legend(4,200,c(IUCN Terrestrial,IUCN Marine, National Terrestrial,National Marine), fill=c(lightblue,blue,lightgreen,green)) If you only need this one illustration, that is probably the easiest thing to do. You can add the appropriate title, axis labels and x-axis tick labels to finish it off. If you need to do a lot of this, it could be wrapped up in a little function that would incorporate or call the barstack function. Jim __ 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 plot stacked histogram in R?
On 05/02/2012 02:58 PM, Manish Gupta wrote: Hi, I am working on data analysis. I need to plot stacked histogram for two Files. File1: 1 2 3 3 4 4 File2: 4 5 6 6 7 7 7 How can i plot them on same graph? Hi Manish, Have a look at the third example for the barp function (plotrix). Jim __ 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] Two ecdf with log-scales
Hi, i want to plot empirical cumulative density functions for two variables in one plot. For better visualizing the differences in the two cumulative curves I'd like to log-scale the axis. So far I found 3 possible functions to plot ecdf: 1) ecdf() from the package 'stats'. I don't know how to successfully set the log.scales? Combining two plots is not a problem: plot(ecdf(x1)) lines(ecdf(x2),col.h=red) 2) gx.ecdf() from package 'rgr'. It is easily possible to plot log-scales, but I don't know how to plot two densities? gx.ecdf(x1,log=TRUE,ifqs = TRUE) 3) Ecdf() from package 'Hmisc'. No log-option directly available and here I also don't know how to 'stack' two plots... Ecdf(x1,what=F) Probably there are many more solutions (e.g. ggplot etc.)... ...Has anyone faced a similar task and found a simple solution? Any suggestions are welcome! Best regards, Johannes -- Jetzt informieren: http://mobile.1und1.de/?ac=OM.PW.PW003K20328T7073a __ 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 can I read the text or character string from a txt file?
If the symbols are separated by spaces, try: scan(yourFile, what = '') Sent from my iPad On May 2, 2012, at 2:36, jpm miao miao...@gmail.com wrote: Hello, I have a large number of time series, which needs to be transformed by log or difference. Some of them are just processed by level (LV) without any transformation. For that purpose, I produce a text file (.csv or .xls) as follows: DLN DLNDLN LV LV LV... How can I read the preceding strings so that I can easily access them, i.e., S[1]=DLN, S[2]=DLN, S[3]=DLN, S[4]=LV,S[5]=LV,S[6]=LV? I tried read.csv and read.table, but they don't work well. If I can access the string, then I will be able to write an if statement so that If the string is DLN, then take log and then difference. If the string is LV, then just keep it as it is. Thanks, miao [[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 read ANOVA output
My experience is the opposite -- the web is filled with introductory statistics material, some of it quite good. If you google for introduction to anova textbook the first hit seems to give exactly what you are asking for. The fifth one down the list also looks good (http://vassarstats.net/textbook/ch13pt1.html). And that's just what you get for free! If you want more you can buy a textbook. I don't understand why you are reluctant to take this advice, or why you think someone here is going to be able to explain it better than a good textbook will. Best, Ista On Wed, May 2, 2012 at 1:37 AM, aRghh sydney.ver...@gmail.com wrote: Hey all who have responded to this post. I am a newbie to ANOVA analysis in R, and let me tell you- resources for us learners are scant, horrible, unclear, imprecise.. in other words.. the worst ever. So advice like go look it up in your classical textbook or on google is not helpful at all. I am scouring posts like these to try to find some kind soul who not only understands the basics, but is willing to help us new folk out.. sadly.. here is not the place. -- View this message in context: http://r.789695.n4.nabble.com/How-to-read-ANOVA-output-tp2329457p4602403.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] Referencing factors through their equivalent numeric level
On 02-05-2012, at 07:22, Kaushik Krishnan wrote: Hey folks I'm sorry for bringing what must be a very simple question to R-help, but after some research I haven't been able to find a solution to my problem. Suppose I create a simple factor: [code] x-c(A,B,B,C,A) x [1] A B B C A x - as.factor(x) x [1] A B B C A Levels: A B C [/code] Now, when I see this factor in terms of its numeric level values, I get [code] as.numeric(x) [1] 1 2 2 3 1 [/code] Suppose I have [code] y - 2 [/code] I want the numeric value of y to reference the level of factor x. That is, I am looking for a function (`foo') so that I will get the following [code] foo(y) #or maybe foo(y,x) [1] B [/code] I can think of a roundabout way of doing through a user defined function, but I am sure that there is a built-in function that offers this functionality. I'd be grateful if someone could tell me what that function is. Maybe this? levels(x)[y] Berend __ 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] Clustering analysis with ordination plots
Please read the posting guide for future questions. I presume you mean using the vegan package? If so, then see this blog post of mine which shows how to do something similar: http://wp.me/pZRQ9-73 If you post more details and an example I will help further if the blog post is not sufficient for you to get the solution you want. G On Mon, 2012-04-30 at 09:44 -0700, borinot wrote: Hello to all, I'm new to R so I have a lot of problems with it, but I'll only ask the main one. I have clustered an environmental matrix with 2 different methods, and I'd like to plot them in a PCA and a db-RDA. I mean, I want see these clusters in the plots like points of differents colours, together with the rest information of the plot, but I don't know how to do this. I've checked a lot of bibliography and forums, and I haven't found the solution... it can't be so hard! Well, thanks in advance! :) -- View this message in context: http://r.789695.n4.nabble.com/Clustering-analysis-with-ordination-plots-tp4598695.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. -- %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% 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.
Re: [R] VarCorr procedure from lme4
I've run into this situation and have been able to prevent problems by using lme4::VarCor(...) Benjamin Nutter | Biostatistician | Quantitative Health Sciences Cleveland Clinic | 9500 Euclid Ave. | Cleveland, OH 44195 | (216) 445-1365 -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of David Stevens Sent: Tuesday, May 01, 2012 9:58 PM To: r-help@r-project.org Subject: Re: [R] VarCorr procedure from lme4 That was it - detaching 'nlme' was the trick. Thanks Walmes and the rest. David On 5/1/2012 7:47 PM, David Stevens wrote: Yes - I also have nlme. Bad juju? David On 5/1/2012 1:32 PM, Walmes Zeviani wrote: It could be a bad coexistence between packages in the same R session. Are you using nlme and/or doBy packages too? Bests. Walmes. = = Walmes Marques Zeviani LEG (Laboratório de Estatística e Geoinformação, 25.450418 S, 49.231759 W) Departamento de Estatística - Universidade Federal do Paraná fone: (+55) 41 3361 3573 VoIP: (3361 3600) 1053 1173 e-mail: wal...@ufpr.br twitter: @walmeszeviani homepage: http://www.leg.ufpr.br/~walmes linux user number: 531218 = = [[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. -- David K Stevens, P.E., Ph.D., Professor Civil and Environmental Engineering Utah Water Research Laboratory 8200 Old Main Hill Logan, UT 84322-8200 435 797 3229 - voice 435 797 1363 - fax david.stev...@usu.edu [[alternative HTML version deleted]] === Please consider the environment before printing this e-mail Cleveland Clinic is ranked one of the top hospitals in America by U.S.News World Report (2010). Visit us online at http://www.clevelandclinic.org for a complete listing of our services, staff and locations. Confidentiality Note: This message is intended for use\...{{dropped:13}} __ 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] Define lower-upper bound for parameters in Optim using Nelder-Mead method
Thanks for this good idea ! Arnaud 2012/5/1 Ted Harding ted.hard...@wlandres.net On 01-May-2012 19:58:41 Arnaud Mosnier wrote: Dear UseRs, Is there a way to define the lower-upper bounds for parameters fitted by optim using the Nelder-Mead method ? Thanks, Arnaud The Nelder-Mead method does not provide built-in capability to set bounds on the range of paramaters. However, you can achieve it by hand by re-defining the function being minimised, so that it tests whether an out-of-range parameter parameter value is being used. If not out-of-range, then return the standard value of the function. If out-of range, then return a very large value. Nelder-Mead will very happily bounce off high walls of this kind, and if the minimum of the function is at the wall will happily converge as close to it as you please. Hoping this helps, Ted. - E-Mail: (Ted Harding) ted.hard...@wlandres.net Date: 01-May-2012 Time: 22:39:15 This message was sent by XFMail - [[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] error in La.svd Lapack routine 'dgesdd'
Dear R Users, I have an unbalanced panel with (on average) approx. 100 individuals over 1370 time intervals (with individual time series of different lengths, varying between 60 and 1370 time intervals). I use the following model: res1-plm(x~c+d+e,data=pdata_frame, effect=twoways, model=within, na.action=na.omit)) I repeatedly get the following error (which has been discussed in the past): Error in La.svd(x, nu, nv) : error code 1 from Lapack routine ‘dgesdd’ I found it hard to create a reproducible example. As noted by Douglas Bates, the error might be related to the scaling of the matrix. For variables x,c,d,and e in object pdata_frame, I find that all sd() are reasonably similar both among the cross-sections as well as among the variables. However, I find that extracting the demeaned data from plm(), variables demXt$d and demXt$e (i.e. the demeaned variables) have sd()s that are very small compared to those of dem_yt and demXt$c (approx. by factor 1e-15). I extract the demeaned data as follows: dem_yt-pmodel.response(res) demXt-model.matrix(res) How is this possible? What is it that plm() does with my data so that the standard deviations change? I suspect effect=twoways to play a central role because plm() works fine for effect=individual. I thought about the idea that maybe, time-effects simply do not apply here. However: In order to test my regression for time-effects (which I detect for subsamples (by time) and for equation x~e at high levels of significance), I need both the model with and and the model without time effects (as otherwise, I can't compare the two models in an F-test), right? Any alternative tests? Another thought was that the impact of d and e changes over time (as in the subsamples I do see such a change). Any help is appreciated! Best wishes, Philipp Grueber - EBS Universitaet fuer Wirtschaft und Recht FARE Department Wiesbaden/ Germany http://www.ebs.edu/index.php?id=finaccL=0 -- View this message in context: http://r.789695.n4.nabble.com/error-in-La-svd-Lapack-routine-dgesdd-tp2125052p4603097.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] Hypothesis Testing using Wald Criterion for two regression models with dummy variables
On May 1, 2012, at 22:01 , meredith wrote: I have two models, controlled by dummy variables to see if the models can be combined into one model with similar intercepts and slopes. Has anyone tried to conduct this type of test in R. I am utilizing the econometric idea of hypothesis testing through the hypothesis of coincidence. I have tried to run an anova with test of Chisq, but I am not sure what the results are telling. In addition, I used the rms package with a lrm model in an anova test, again I am not sure what the results are telling me: Can anyone help me with this? Not unless you say what you are trying to do... As far as I can tell, you are (A) using a chi-square test for a standard linear model (Gaussian response) and (B) fitting a logistic regression model to the same response, which assumes that it is a proportion or binary response. Neither makes any sense to me. -- Peter Dalgaard, Professor Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Email: pd@cbs.dk Priv: pda...@gmail.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] 2nd call for chapters: book Data Mining Applications with R; due by 31 May 2012
Book title: Data Mining Applications with R Publisher: Elsevier URL: http://www.rdatamining.com/books/book2 Due date: 2nd round of chapter proposals due by 31 May 2012 Potential authors are expected to submit a 1-2 page manuscript proposal clearly explaining the mission and concerns of the proposed chapter. See details at http://www.rdatamining.com/books/book2. __ 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] PLS validation value
Greetings R users, My interest in the Q2cum score comes my endeavor to replicate SIMCAP PLS-DA analysis in R. I use the exact same dataset. After doing the analysis in R, I can get the exact same R2Ycum. However, the Q2cum is significantly off. Adding the Q2cum of the 1st and 2nd component comes close but that seems unconvincing and I don't understand why the 3rd component Q2cum would be so far off. Below is the code and output: pls.reg.new=plsreg2(newserumvars.sc, newtimematrix, nc=3) pls.reg.new$expvar #this provides the exact R2Y I get in SIMCAP pls.reg.new$Q2cum The Q2cum values should be close to component 1 = .2149 component 2 = .4578 *component 3 = .6627* #value of concern All of the R output values are close for the respective class except for the final Q2cum value: Q2cum.B Q2cum.FR8 Q2cum.S45 Q2cum t1-0.05460.39920.2973 0.2140 t2 0.28630.38240.7039 0.4573 t3 0.58390.74300.6980 *0.3735 *#*not close* Done. I have read that the plspm package used LOO cross validation. SIMCAP uses the same method, however it leaves '7' out instead. Perhaps this might be an issue that results in this difference? Any insight or assistance would be most appreciated. I certainly appreciate any time you take to answer my question. Regards, Charles Determan [[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] list objects calculation
Hi you maybe can use mapply If you have 2 lists xl-list(x, x+5) xl [[1]] [1] 1 2 3 4 5 [[2]] [1] 6 7 8 9 10 yl-list(9,10) yl [[1]] [1] 9 [[2]] [1] 10 and this function fff- function(xl,yl) (xl-yl)/yl mapply(fff, xl, yl) [,1] [,2] [1,] -0.889 -0.4 [2,] -0.778 -0.3 [3,] -0.667 -0.2 [4,] -0.556 -0.1 [5,] -0.444 0.0 gives you probably desired result. Regards Petr I have two kinds of list, for example, one is like t[[1]]= 1 6 2 7 3 8 4 9 5 10 ... t[[731]] the other is k[[1]]= 9 10 ... k[[731]] I want to have a new list,like x x[[1]]= (1-9)/9(6-10)/10 (2-9)/9(7-10)/10 (3-9)/9(8-10)/10 (4-9)/9(9-10)/10 (5-9)/9(10-10)/10 ... x[[731]] How should I do? Thank you. -- View this message in context: http://r.789695.n4.nabble.com/list-objects- calculation-tp4602437.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] Formal test for proportional subdistribution hazards assumption
L.s. I want to test the proportional subdistribution hazards assumption for several competing risk regression models I fitted using the crr()-function (cmprsk-package). I am able to plot the Schoenfeld-type residuals against failure time, but in some cases I doubt whether the assumption holds or not, so I was wondering whether a formal test analogous to the cox.zph for Cox-regression models exists for crr? Thanks, Rob van Kruijsdijk University Medical Centre Utrecht -- De informatie opgenomen in dit bericht kan vertrouwelijk zijn en is uitsluitend bestemd voor de geadresseerde. Indien u dit bericht onterecht ontvangt, wordt u verzocht de inhoud niet te gebruiken en de afzender direct te informeren door het bericht te retourneren. Het Universitair Medisch Centrum Utrecht is een publiekrechtelijke rechtspersoon in de zin van de W.H.W. (Wet Hoger Onderwijs en Wetenschappelijk Onderzoek) en staat geregistreerd bij de Kamer van Koophandel voor Midden-Nederland onder nr. 30244197. Denk s.v.p aan het milieu voor u deze e-mail afdrukt. -- This message may contain confidential information and is...{{dropped:12}} __ 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] date and time conversion
Hi I've been trying to convert numbers from an online temperature database into dates and time that R recognizes. the problem is that the database has put a T between the numbers and R will not accept any conversions. this is the format that it's in now 1981-01-02T08:00 can anyone help? cheers! -- View this message in context: http://r.789695.n4.nabble.com/date-and-time-conversion-tp4602786.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.
[R] convert numbers into dates and time
Hi I've been trying to convert numbers from an online temperature database into dates and time that R recognizes. the problem is that the database has put a T between the numbers and R will not accept any conversions. this is the format that it's in now 1981-01-02T08:00 can anyone help? cheers! -- View this message in context: http://r.789695.n4.nabble.com/convert-numbers-into-dates-and-time-tp4602708.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] factor conversion to date/time
Hi, I've been trying to convert numbers from an online temperature database into dates and time that R recognizes. I've tried as.Date, as.POSIXlt and strptime the problem is that the database has put a T between the numbers and R will not accept any conversions. currently it sees the date as a factor with the format as 1981-01-02T08:00I would like to keep only the year and month, but my primary focus is to get R to recognize it as a date. Thank you for your help. cheers,Marjolein [[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] scanning a data set for strings
Hello, I'm looking for what I'm sure is a quick answer. I'm working with a data set that looks like this: Week Game.ID VTm VPts HTm HPts Differential HomeWin 11 NFL_20050908_OAK@NE OAK 20 NE 30 10 FALSE 21 NFL_20050911_ARI@NYGARI 19 NYG 42 23 FALSE 31 NFL_20050911_CHI@WAS CHI7 WAS92 FALSE 41 NFL_20050911_CIN@CLECIN 27 CLE13 -14 FALSE 51 NFL_20050911_DAL@SD DAL 28 SD 24 -4 FALSE 61 NFL_20050911_DEN@MIA DEN 10 MIA34 24 FALSE NFL data. I want to pair each team with the points they received at home and away and create another table showing this. I know it's easy to do, but all the methods I am coming up with involve doing each team individually via a for loop that searches for [i,5]==NE, [i,5]==NYG. I would then use the same method to pair the same team code (NYG or NE) with VPTs when it's Visiting. Thanks for the help. -- View this message in context: http://r.789695.n4.nabble.com/scanning-a-data-set-for-strings-tp4602953.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] How to read ANOVA output
Or look for A handbook of Statistical Analyses using R. (Everitt and Holhorn) available on line in pdf format. John Kane Kingston ON Canada -Original Message- From: istaz...@gmail.com Sent: Wed, 2 May 2012 07:01:22 -0400 To: sydney.ver...@gmail.com Subject: Re: [R] How to read ANOVA output My experience is the opposite -- the web is filled with introductory statistics material, some of it quite good. If you google for introduction to anova textbook the first hit seems to give exactly what you are asking for. The fifth one down the list also looks good (http://vassarstats.net/textbook/ch13pt1.html). And that's just what you get for free! If you want more you can buy a textbook. I don't understand why you are reluctant to take this advice, or why you think someone here is going to be able to explain it better than a good textbook will. Best, Ista On Wed, May 2, 2012 at 1:37 AM, aRghh sydney.ver...@gmail.com wrote: Hey all who have responded to this post. I am a newbie to ANOVA analysis in R, and let me tell you- resources for us learners are scant, horrible, unclear, imprecise.. in other words.. the worst ever. So advice like go look it up in your classical textbook or on google is not helpful at all. I am scouring posts like these to try to find some kind soul who not only understands the basics, but is willing to help us new folk out.. sadly.. here is not the place. -- View this message in context: http://r.789695.n4.nabble.com/How-to-read-ANOVA-output-tp2329457p4602403.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. GET FREE SMILEYS FOR YOUR IM EMAIL - Learn more at http://www.inbox.com/smileys Works with AIM®, MSN® Messenger, Yahoo!® Messenger, ICQ®, Google Talk™ and most webmails __ 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] Multiple plots
I have a variable : *sim.var[,1] * Object of class SpatialPixelsDataFrame Object of class SpatialPixels Grid topology: cellcentre.offset cellsize cells.dim Xloc 0.3 0.0597 Yloc 0.1 0.05 117 SpatialPoints: Xloc Yloc [1,] 0.30 1.70 [2,] 0.35 1.70 [3,] 0.35 1.75 [4,] 0.40 1.70 [5,] 0.40 1.75 [6,] 0.40 1.80 [7,] 0.40 1.85 [8,] 0.40 1.90 [9,] 0.40 2.10 [10,] 0.40 2.15 [11,] 0.40 2.20 [12,] 0.40 2.40 [13,] 0.40 2.45 and a variable : *sim.mean[,1]* Object of class SpatialPixelsDataFrame Object of class SpatialPixels Grid topology: cellcentre.offset cellsize cells.dim Xloc 0.3 0.0597 Yloc 0.1 0.05 117 SpatialPoints: Xloc Yloc [1,] 0.30 1.70 [2,] 0.35 1.70 [3,] 0.35 1.75 [4,] 0.40 1.70 [5,] 0.40 1.75 [6,] 0.40 1.80 [7,] 0.40 1.85 [8,] 0.40 1.90 [9,] 0.40 2.10 [10,] 0.40 2.15 [11,] 0.40 2.20 If I plot these variables with: *spplot(sim.var[,1],main=var)* and *spplot(sim.mean[,1],main=mean)* it works. But how can I plot these two variables together with a single scale? Thanks -- View this message in context: http://r.789695.n4.nabble.com/Multiple-plots-tp4603205.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] DepmixS4
Deepak, On Wed, May 2, 2012 at 7:53 AM, deepakw deepakwarr...@gmail.com wrote: Hi I am trying to use depmixS4 package. Based on the documentation, it seems that depmix allows one to fit an HMM model based on a training data with time-varying co-variates. However, I did not find any routines which can help test the accuracy on the fitted HMM model on out-of-sample data. Can someone confirm if that is indeed the case? depmixS4 does not have functionality for forecasting/state prediction and similar if that is what you are after. Also are there any alternate packages for the same? Not sure whether other packages can do that in combination with time-varying co-variates. Best, Ingmar Thanks -Deepak -- View this message in context: http://r.789695.n4.nabble.com/DepmixS4-tp4602417.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. [[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] Hypothesis Testing using Wald Criterion for two regression models with dummy variables
Meredith: You are clearly out of your depth. Get local help. R-help is, err, an R help list, not a resource for remote statistical consulting. Although, I admit, there is often some overlap. -- Bert On Wed, May 2, 2012 at 5:58 AM, peter dalgaard pda...@gmail.com wrote: On May 1, 2012, at 22:01 , meredith wrote: I have two models, controlled by dummy variables to see if the models can be combined into one model with similar intercepts and slopes. Has anyone tried to conduct this type of test in R. I am utilizing the econometric idea of hypothesis testing through the hypothesis of coincidence. I have tried to run an anova with test of Chisq, but I am not sure what the results are telling. In addition, I used the rms package with a lrm model in an anova test, again I am not sure what the results are telling me: Can anyone help me with this? Not unless you say what you are trying to do... As far as I can tell, you are (A) using a chi-square test for a standard linear model (Gaussian response) and (B) fitting a logistic regression model to the same response, which assumes that it is a proportion or binary response. Neither makes any sense to me. -- Peter Dalgaard, Professor Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Email: pd@cbs.dk Priv: pda...@gmail.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. -- Bert Gunter Genentech Nonclinical Biostatistics Internal Contact Info: Phone: 467-7374 Website: http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm __ 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] factor conversion to date/time
On 02/05/2012 8:08 AM, marjolein post wrote: Hi, I've been trying to convert numbers from an online temperature database into dates and time that R recognizes. I've tried as.Date, as.POSIXlt and strptime the problem is that the database has put a T between the numbers and R will not accept any conversions. currently it sees the date as a factor with the format as 1981-01-02T08:00I would like to keep only the year and month, but my primary focus is to get R to recognize it as a date. To stop the conversion to factors, use argument stringsAsFactors=FALSE when you read the file, or even better, options(stringsAsFactors=FALSE) for a global change. To convert a string, specify the format (following the instructions in ?strptime): x - 1981-01-02T08:00I strptime(x, format=%Y-%m-%dT%H:%MI) 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.
Re: [R] Numeric data not numeric in .csv file
On Wed, May 2, 2012 at 4:34 AM, Jim Lemon j...@bitwrit.com.au wrote: On 05/02/2012 10:47 AM, Eve Proper wrote: I am a raw novice to R, playing around with a mini .csv dataset created in Excel. I can read it in and the data looks OK in Excel and upon initial inspection in R: hikes- read.csv(/Users/eproper/Desktop/hikes.csv, header=TRUE) print(hikes) does exactly what it is supposed to do. Two of the variables are genuine strings, but the others ought to be numeric, and R will calculate their min, max etc. However, is.numeric returns FALSE for all of them; storage.mode returns language. as.numeric returns Error: 'pairlist' object cannot be coerced to type 'double'. In what I suspect is a related problem, any command that calls for a variable name requires an initial ~ to work. That is, instead of plot(miles) I have to use plot(~miles). No doubt there is some very elementary mistake I am making, but I can't figure it out. Any help would be appreciated. Hi Eve, Have you tried as.numeric on them? As Jeff suggested, you may be importing spaces along with the digits or some other character that changes the class of the variable. Also note that the default behavior of functions like read.csv is to coerce all of the values in a column of the resulting data frame to the lowest common denominator. If you have one text value in a column of numbers, you usually get factor values. This is due to the restriction that all values in a column must be of the same class (data type). Jim If accidentally coerced to factors, the OP might prefer as.numeric(as.character(x)) to get the apparent numeric values rather than the internal ones. Also seconded Jeff's advice about str() Michael __ 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] scanning a data set for strings
I think you are looking for something like aggregate(cbind(VPts, HPts) ~ VTm + HTm, data = NFL, sum) but you should look at the examples for ?aggregate to tweak it to what you need. Michael On Wed, May 2, 2012 at 7:45 AM, Daniel_55 serna.da...@gmail.com wrote: Hello, I'm looking for what I'm sure is a quick answer. I'm working with a data set that looks like this: Week Game.ID VTm VPts HTm HPts Differential HomeWin 1 1 NFL_20050908_OAK@NE OAK 20 NE 30 10 FALSE 2 1 NFL_20050911_ARI@NYG ARI 19 NYG 42 23 FALSE 3 1 NFL_20050911_CHI@WAS CHI 7 WAS 9 2 FALSE 4 1 NFL_20050911_CIN@CLE CIN 27 CLE 13 -14 FALSE 5 1 NFL_20050911_DAL@SD DAL 28 SD 24 -4 FALSE 6 1 NFL_20050911_DEN@MIA DEN 10 MIA 34 24 FALSE NFL data. I want to pair each team with the points they received at home and away and create another table showing this. I know it's easy to do, but all the methods I am coming up with involve doing each team individually via a for loop that searches for [i,5]==NE, [i,5]==NYG. I would then use the same method to pair the same team code (NYG or NE) with VPTs when it's Visiting. Thanks for the help. -- View this message in context: http://r.789695.n4.nabble.com/scanning-a-data-set-for-strings-tp4602953.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] date and time conversion
Quick and dirty solution is to use sub() to change the T to a space and then use as.POSIXct as usual. x - 1981-01-02T08:00 as.POSIXct(sub(T, , x), format = %Y-%m-%d %H:%M) but it does look to me like R can work around the T if you give a good format argument: as.POSIXct(x, format = %Y-%m-%dT%H:%M) Michael On Wed, May 2, 2012 at 6:10 AM, mpostje mayo_j...@hotmail.com wrote: Hi I've been trying to convert numbers from an online temperature database into dates and time that R recognizes. the problem is that the database has put a T between the numbers and R will not accept any conversions. this is the format that it's in now 1981-01-02T08:00 can anyone help? cheers! -- View this message in context: http://r.789695.n4.nabble.com/date-and-time-conversion-tp4602786.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. __ 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] factor conversion to date/time
Please don't triple post. Michael On Wed, May 2, 2012 at 8:08 AM, marjolein post mayo_j...@hotmail.com wrote: Hi, I've been trying to convert numbers from an online temperature database into dates and time that R recognizes. I've tried as.Date, as.POSIXlt and strptime the problem is that the database has put a T between the numbers and R will not accept any conversions. currently it sees the date as a factor with the format as 1981-01-02T08:00I would like to keep only the year and month, but my primary focus is to get R to recognize it as a date. Thank you for your help. cheers,Marjolein [[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] Hypothesis Testing using Wald Criterion for two regression models with dummy variables
Peter- Maybe I have not articulately my problem clearly, I have had local help with the statistical part just trying to figure out how to correctly program this test. For clarity's sake, I have months worth of data, I want to potentially combine those months into four, shall we say seasons, that have close to the same behaviour. Therefore to do this, I am trying a monthly moving window to categorize these seasons. After talking to a couple water resources statisician's we decided the way to test if the months are different is through the use of hypothesis testing and a dummy variable. So I have one regression, Model A, that includes a zero in the dummy spot with the two months of data combined, then I have another regression, Model B, that includes the interaction term for the changes between the months (the intercept changes, using a 0 or 1 dummy variable). Now we discussed running a Wald testing, Chi squared, to test to see if the interaction term is of importance probability wise, can I do this utilizing anova? Does this make more sense? Then I will run another set of restricted and unrestricted models to account for potential differences in the mean (i.e the slope). Does this explain my problem better? Meredith -- View this message in context: http://r.789695.n4.nabble.com/Hypothesis-Testing-using-Wald-Criterion-for-two-regression-models-with-dummy-variables-tp4601582p4603260.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] Numeric data not numeric in .csv file
On May 1, 2012, at 8:47 PM, Eve Proper wrote: I am a raw novice to R, playing around with a mini .csv dataset created in Excel. I can read it in and the data looks OK in Excel and upon initial inspection in R: hikes - read.csv(/Users/eproper/Desktop/hikes.csv, header=TRUE) print(hikes) does exactly what it is supposed to do. Two of the variables are genuine strings, but the others ought to be numeric, and R will calculate their min, max etc. However, is.numeric returns FALSE for all of them; How did you do this? What code did you use? It should have been: lapply(hikes, is.numeric) storage.mode returns language. Well, that suggests that you were trying to use unquoted variable names without the data objects name. Did you use attach() on the basis of some misguided instructions? as.numeric returns Error: 'pairlist' object cannot be coerced to type 'double'. In what I suspect is a related problem, any command that calls for a variable name requires an initial ~ to work. That is, instead of plot(miles) I have to use plot(~miles). As I said, you are not correctly referencing column names within data objects. No doubt there is some very elementary mistake I am making, but I can't figure it out. Any help would be appreciated. http://theturducken.blogspot.com/ [[alternative HTML version deleted]] And you should read the Posting Guide and correct your posting format. __ 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 Winsemius, MD Heritage Laboratories West Hartford, CT __ 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] calibration of Garch models to historical data
This might be more of a question for R-SIG-Finance and followup should probably be there, but you might get a start with the rugarch package. Michael On Wed, May 2, 2012 at 4:13 AM, Ivette iva_mihayl...@mail.ru wrote: I have done the usual estimation of GARCH models, applied to my historical dataset (commodities futures) with a maximum likelihood function and selected the best model on the basis of information criteria such as Akaike and Bayes. Can somebody explain me please the calibration scheme for a GARCH model? I was not able to find a paper, dealing with exactly this algorithm for my case. I only understood that I have to compare the performance of the best GARCH model (from the estimation step), fitted to my historical dataset and a GARCH simulation (let's abbreviate this Squared Error difference to E2). However, it is not clear to me: - with what parameters' values to start this simulation, - how many times it is normal to perform it, and - what to compare via E2 (maximum likelihood values, or parameter values) - how to constructassess E2 for the GARCH case. Thank you in advance for your suggestions. Ivette -- View this message in context: http://r.789695.n4.nabble.com/calibration-of-Garch-models-to-historical-data-tp4602606.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] Arules and different item columns with same item labelsŠ.
It is not clear what you mean. Can you supply some sample data? Have a look at ?dput for a handy way to supply data. John Kane Kingston ON Canada -Original Message- From: lterle...@anadolu.edu.tr Sent: Tue, 1 May 2012 17:55:25 + To: r-help@r-project.org Subject: [R] Arules and different item columns with same item labelsŠ. Dear Users, I have data that have different data columns (hair color, eye color, etc. ) with same item labels and I do not want to recode them like haircolor=brown, etc. Is it possible to do it automatically? Thanks right now for your tips and given directions. -- Levent TERLEMEZ [[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. Receive Notifications of Incoming Messages Easily monitor multiple email accounts access them with a click. Visit http://www.inbox.com/notifier and check it out! __ 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] coxph reference hazard rate
As has been answered several times on rhelp ... the baseline hazard is for a case with the mean value. It's not a meaningful case with all factor variables. There can be no cases where fidelity3 has a fractional value. You should be using predict() and survfit() to display estimates for particular meaningful cases. You might want to use a different rhs formula as well because the one offered omits the main effects. Choosing ~bucket*factor(fidelity 3) would include those terms. -- David. On May 1, 2012, at 8:37 PM, Georges Dupret wrote: Hi, In the following results I interpret exp(coef) as the factor that multiplies the base hazard rate if the corresponding variable is TRUE. For example, when the bucket is ks008 and fidelity = 3, then the rate, compared to the base rate h_0(t), is h(t) = 0.200 h_0(t). My question is then, to what case does the base hazard rate correspond to? I would expect the reference to be the first factor value, i.e. bucket jpc001 with fidelity = 3, but its exp(coef) is not one. I verified the contrasts, and the row corresponding to the first factor value is zero everywhere; moreover, I didn't change the default, so a bad setting of the contrasts doesn't seem to be the issue. Best, ge Call: coxph(formula = Surv(time, event = (censored == FALSE)) ~ bucket:factor(fidelity 3), data = week.15) coef exp(coef) se(coef) z p bucketjpc001:factor(fidelity 3)FALSE -1.606 0.201 0.00624 -257.5 0 bucketks006:factor(fidelity 3)FALSE -1.613 0.199 0.00627 -257.5 0 bucketks007:factor(fidelity 3)FALSE -1.620 0.198 0.00626 -258.8 0 bucketks008:factor(fidelity 3)FALSE -1.611 0.200 0.00625 -257.6 0 bucketks009:factor(fidelity 3)FALSE -1.620 0.198 0.00626 -258.9 0 bucketks010:factor(fidelity 3)FALSE -1.619 0.198 0.00626 -258.6 0 bucketjpc001:factor(fidelity 3)TRUE -0.156 0.856 0.00596 -26.2 0 bucketks006:factor(fidelity 3)TRUE -0.171 0.842 0.00600 -28.6 0 bucketks007:factor(fidelity 3)TRUE -0.168 0.845 0.00602 -28.0 0 bucketks008:factor(fidelity 3)TRUE -0.167 0.846 0.00600 -27.8 0 bucketks009:factor(fidelity 3)TRUE -0.170 0.844 0.00599 -28.4 0 bucketks010:factor(fidelity 3)TRUE NANA 0.0 NA NA Likelihood ratio test=294562 on 11 df, p=0 n= 1173838, number of events= 629383 -- View this message in context: http://r.789695.n4.nabble.com/coxph-reference-hazard-rate-tp4602092.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. David Winsemius, MD Heritage Laboratories West Hartford, CT __ 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 results from a median polish
write.csv() is definitely the right way to go so you're on track What is str(medpolish)? From the error message, it sounds like it's a functionIf it is, are you sure you don't mean write.csv(medpolish( xx )) ? Michael On Wed, May 2, 2012 at 12:39 AM, Martin Raymond Lefebvre mlefe...@uwo.ca wrote: Quick question from a new user to R, How do I extract my solution of a median polish matrix from R to a spreadsheet file such as .csv? From my reading of my guide book (R for SPSS and SAS users version 2), I deduce that exporting a file to .csv would look like the following: write.csv(medpolish, file =outfilename.csv, row.names = FALSE) , by I get the following: Error in as.data.frame.default(x[[i]], optional = TRUE) : cannot coerce class 'function' into a data.frame So far I've been copy/pasting segment by segment into Excel and running text2column, but there has got to be a better way. Martin R. Lefebvre [[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] Two ecdf with log-scales
On May 2, 2012, at 6:14 AM, Johannes Radinger wrote: Hi, i want to plot empirical cumulative density functions for two variables in one plot. For better visualizing the differences in the two cumulative curves I'd like to log-scale the axis. So far I found 3 possible functions to plot ecdf: 1) ecdf() from the package 'stats'. I don't know how to successfully set the log.scales? Combining two plots is not a problem: plot(ecdf(x1)) lines(ecdf(x2),col.h=red) 2) gx.ecdf() from package 'rgr'. It is easily possible to plot log- scales, but I don't know how to plot two densities? gx.ecdf(x1,log=TRUE,ifqs = TRUE) 3) Ecdf() from package 'Hmisc'. No log-option directly available and here I also don't know how to 'stack' two plots... Ecdf(x1,what=F) Probably there are many more solutions (e.g. ggplot etc.)... ...Has anyone faced a similar task and found a simple solution? Any suggestions are welcome! Have you searched the Archives? I seem to remember that the log(0) was a barrier to persons attempting this in the past. (ISTR a posting in the last few weeks.) Maybe you could also provide a test data object that has the same range as your x1 and x 2 variables. and provide commented, minimal, self-contained, reproducible code. -- David Winsemius, MD West Hartford, CT __ 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] factor conversion to date/time
Try something like this. Convert the vector to character and grab the first 10 characters then convert to a date. aa - as.factor(1981-01-02T08:00I) aa - as.character(aa) aa - substr(aa, 1, 10) class(b) John Kane Kingston ON Canada -Original Message- From: mayo_j...@hotmail.com Sent: Wed, 2 May 2012 14:08:26 +0200 To: r-help@r-project.org Subject: [R] factor conversion to date/time Hi, I've been trying to convert numbers from an online temperature database into dates and time that R recognizes. I've tried as.Date, as.POSIXlt and strptime the problem is that the database has put a T between the numbers and R will not accept any conversions. currently it sees the date as a factor with the format as 1981-01-02T08:00I would like to keep only the year and month, but my primary focus is to get R to recognize it as a date. Thank you for your help. cheers,Marjolein [[alternative HTML version deleted]] FREE ONLINE PHOTOSHARING - Share your photos online with your friends and family! Visit http://www.inbox.com/photosharing to find out more! __ 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] Hypothesis Testing using Wald Criterion for two regression models with dummy variables
On May 2, 2012, at 15:48 , meredith wrote: Peter- Maybe I have not articulately my problem clearly, I have had local help with the statistical part just trying to figure out how to correctly program this test. For clarity's sake, I have months worth of data, I want to potentially combine those months into four, shall we say seasons, that have close to the same behaviour. Therefore to do this, I am trying a monthly moving window to categorize these seasons. After talking to a couple water resources statisician's we decided the way to test if the months are different is through the use of hypothesis testing and a dummy variable. So I have one regression, Model A, that includes a zero in the dummy spot with the two months of data combined, then I have another regression, Model B, that includes the interaction term for the changes between the months (the intercept changes, using a 0 or 1 dummy variable). Now we discussed running a Wald testing, Chi squared, to test to see if the interaction term is of importance probability wise, can I do this utilizing anova? Does this make more sense? Then I will run another set of restricted and unrestricted models to account for potential differences in the mean (i.e the slope). Does this explain my problem better? Not really. It does indicate that Bert is right, though: You need to enlist a local statistician. There are things clearly not understood, which we cannot help you with on this list. -pd PS. This is a mailing list. Please quote context. Meredith -- View this message in context: http://r.789695.n4.nabble.com/Hypothesis-Testing-using-Wald-Criterion-for-two-regression-models-with-dummy-variables-tp4601582p4603260.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. -- Peter Dalgaard, Professor Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Email: pd@cbs.dk Priv: pda...@gmail.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] selection by two unique variables
Dear Group, I am working with a large dataset where I need to select for each unique id the the unique lastpk row. Here is a sample subject: id wtdt wt lastpk 64050256 2010-09-18 275 2010-09-16 64050256 2010-09-19 277 2010-09-18 64050256 2010-09-20 272 2010-09-18 64050256 2010-09-21 277 2010-09-18 I want the result as: id wtdt wt lastpk 64050256 2010-09-18 275 2010-09-16 64050256 2010-09-19 277 2010-09-18 I am using !(duplicated(data$id)) to select the first row but now I want to select the first row of the unique lastpk in each unique id. I appreciate your help on this. Regards, Ayyappa [[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] rgl.Sweave not producing transparency in pdf plots with alpha
Hi Folks, I'm trying to get rgl.Sweave to produce plots with transparency. However, it just seems to produce opaque plots when pdf is the output type. Perhaps this is a known issue? I'll just use .png in the meantime, but wanted to see about this, as I didn't see it in the documentation (though it's possible I missed it). Thanks, Allie \documentclass{article} \title {rgl test} \usepackage{Sweave} \begin {document} This is a test of rgl.sweave's alpha capability. \begin{figure} % uncomment line below for png output (correct transparency) % echo=FALSE, grdevice=rgl.Sweave, fig=TRUE, width=5, height=5, resolution=100= echo=FALSE, grdevice=rgl.Sweave, fig=TRUE, width=5, height=5, resolution=100, outputtype=pdf, pdf=TRUE= library(rgl) data(volcano) z - 2 * volcano# Exaggerate the relief x - 10 * (1:nrow(z)) # 10 meter spacing (S to N) y - 10 * (1:ncol(z)) # 10 meter spacing (E to W) zlim - range(y) zlen - zlim[2] - zlim[1] + 1 colorlut - terrain.colors(zlen) # height color lookup table col - colorlut[ z-zlim[1]+1 ] # assign colors to heights for each point #open3d() surface3d(x, y, z, color=col, back=lines, alpha=0.75) @ \end{figure} \end{document} __ 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] selection by two unique variables
?tapply ?with is also useful here as in (untested) with(yourdataframe, tapply(lastpk, id, unique)) -- Bert On Wed, May 2, 2012 at 7:58 AM, Ayyappa Chaturvedula ayyapp...@gmail.com wrote: Dear Group, I am working with a large dataset where I need to select for each unique id the the unique lastpk row. Here is a sample subject: id wtdt wt lastpk 64050256 2010-09-18 275 2010-09-16 64050256 2010-09-19 277 2010-09-18 64050256 2010-09-20 272 2010-09-18 64050256 2010-09-21 277 2010-09-18 I want the result as: id wtdt wt lastpk 64050256 2010-09-18 275 2010-09-16 64050256 2010-09-19 277 2010-09-18 I am using !(duplicated(data$id)) to select the first row but now I want to select the first row of the unique lastpk in each unique id. I appreciate your help on this. Regards, Ayyappa [[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. -- Bert Gunter Genentech Nonclinical Biostatistics Internal Contact Info: Phone: 467-7374 Website: http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm __ 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] strange differences in vector operation versus manual calculation
Hi, I'm running a calculation in two ways. The first way is to employ vectors and evaluate a function in one go. The second way is to break down the function into pieces and combine the pieces to the final answer. Algebraically, they should give me the same result. But the final vector differs significantly. I must be missing something very obvious, but I just cannot see it xx - c(-9.56305825951348, -8.20220288142583, -6.84134750333818, -5.48049212525052, -4.11963674716287) params - structure(c(-7.9292094394, 4.9549173134, 4.738588416, 101.5743644892 ), .Names = c(LOG_AC50, HILL_COEF, INF_ACTIVITY, ZERO_ACTIVITY )) yy - params[4] + (params[3] - params[4])/(1 + 10^(params[1]-xx)^params[2]) t1 - 10^(params[1]-xx) t2 - params[3] - params[4] t3 - (1+t1)^params[2] t4 - t2/t3; t5 - params[4] + t4 I would've expected yy and t5 to be the same; yet they are not -- Rajarshi Guha | http://blog.rguha.net NIH Center for Advancing Translational Science __ 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 bars for a barchart
Walmes, Thank you so much!!! I am still trying to understand all of your code but it works. I have changed it a bit so that I get upper and lower limits for the error bar, and that the origin starts at 0 so the negative values are plotted correctly. barchart(Change~fTreat,groups=Process,change, stderr=change$stderr, ylab=Pocertage change, xlab=Treatment, #ylim=-115:50, scales=list(alternating=FALSE, tick.number=7, tck=c(-1,0)), prepanel=function(y, stderr, subscripts=subscripts, ...){ uy - as.numeric(y+stderr[subscripts]) ly - as.numeric(y-stderr[subscripts]) list(ylim=range(y,uy,ly, finite=TRUE)) }, panel= function(x, y, subscripts, groups, stderr, box.ratio, ...){ panel.barchart(x, y, subscripts=subscripts, groups=groups, box.ratio=box.ratio,origin=0, ...) panel.abline(h=0,col=black,...) d - 1/(nlevels(groups)+nlevels(groups)/box.ratio) g - (as.numeric(groups[subscripts])-1); g - (g-median(g))*d panel.arrows(as.numeric(x)+g,y-stderr[subscripts], as.numeric(x)+g, y+stderr[subscripts], code=3,angle=90, length=0.025) } ) I am very new to creating function and would be great if you could explain what the d and g elemens actually do? this is just for me to understand and later maybe make my own functions. I am assuming that g centers the error bars? but d? Regards Beatriz de Francisco Mora PhD Student The Scottish Association for Marine Science Scottish Marine Institute Oban PA37 1QA Tel: 06131 559000 (switchboard) Fax: 01631559001 E. beatriz.defranci...@sams.ac.uk http://www.smi.ac.uk/beatriz-de-franciso From: r-help-boun...@r-project.org [r-help-boun...@r-project.org] on behalf of ilai [ke...@math.montana.edu] Sent: 02 May 2012 04:14 To: Walmes Zeviani Cc: r-help@r-project.org Subject: Re: [R] error bars for a barchart Thank you for your example. I only skimmed it, but since both solutions use nlevels and box.ratio it is no surprise we end up at the same place (although I do think your g-median is nicer than my 3/4). Thing is, I wouldn't call either of these simple... would be nice if one could just query the new centers, but I don't know if there is a way without hacking panel.barchart itself ? Cheers On Tue, May 1, 2012 at 1:34 PM, Walmes Zeviani walmeszevi...@gmail.com wrote: I have a repoducibe example here http://ridiculas.wordpress.com/2011/11/23/media-e-desvio-padrao-de-muitas-variaveis-separado-por-grupos/ Sorry for it be in Portuguese. Walmes. == Walmes Marques Zeviani LEG (Laboratório de Estatística e Geoinformação, 25.450418 S, 49.231759 W) Departamento de Estatística - Universidade Federal do Paraná fone: (+55) 41 3361 3573 VoIP: (3361 3600) 1053 1173 e-mail: wal...@ufpr.br twitter: @walmeszeviani homepage: http://www.leg.ufpr.br/~walmes linux user number: 531218 == __ 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. The Scottish Association for Marine Science (SAMS) is registered in Scotland as a Company Limited by Guarantee (SC009292) and is a registered charity (9206). SAMS has an actively trading wholly owned subsidiary company: SAMS Research Services Ltd a Limited Company (SC224404). All Companies in the group are registered in Scotland and share a registered office at Scottish Marine Institute, Oban Argyll PA37 1QA. The content of this message may contain personal views which are not the views of SAMS unless specifically stated. Please note that all email traffic is monitored for purposes of security and spam filtering. As such individual emails may be examined in more detail. __ 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] strange differences in vector operation versus manual calculation
Your multistep approach corresponds to the following, which has one more set of parentheses than you used yy - params[4] + (params[3] - params[4])/((1 + 10^(params[1]-xx))^params[2]) In R lingo, both of your approaches are vectorized and you probably won't find a huge difference in speed between them. I would use the long approach, as it is more understandable. (I would also give memorable names to the intermediate results, not t1, t2, ..., unless they really had no meaning.) Bill Dunlap Spotfire, TIBCO Software wdunlap tibco.com -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of Rajarshi Guha Sent: Wednesday, May 02, 2012 8:42 AM To: R Subject: [R] strange differences in vector operation versus manual calculation Hi, I'm running a calculation in two ways. The first way is to employ vectors and evaluate a function in one go. The second way is to break down the function into pieces and combine the pieces to the final answer. Algebraically, they should give me the same result. But the final vector differs significantly. I must be missing something very obvious, but I just cannot see it xx - c(-9.56305825951348, -8.20220288142583, -6.84134750333818, -5.48049212525052, -4.11963674716287) params - structure(c(-7.9292094394, 4.9549173134, 4.738588416, 101.5743644892 ), .Names = c(LOG_AC50, HILL_COEF, INF_ACTIVITY, ZERO_ACTIVITY )) yy - params[4] + (params[3] - params[4])/(1 + 10^(params[1]-xx)^params[2]) t1 - 10^(params[1]-xx) t2 - params[3] - params[4] t3 - (1+t1)^params[2] t4 - t2/t3; t5 - params[4] + t4 I would've expected yy and t5 to be the same; yet they are not -- Rajarshi Guha | http://blog.rguha.net NIH Center for Advancing Translational Science __ 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] interactive loop
Dear R-helpers, I have a number of point configurations representing skull shapes, but some of them contain superfluous points. I want to write a loop in which each configuration is plotted and I am asked to write the numbers of points that are superfluous. However, I don't know how to introduce this interactive element. Would you give me an advice? Best regards Ondřej Mikula -- Ondřej Mikula Institute of Animal Physiology and Genetics Academy of Sciences of the Czech Republic Veveri 97, 60200 Brno, Czech Republic Institute of Vertebrate Biology Academy of Sciences of the Czech Republic Studenec 122, 67502 Konesin, Czech Republic __ 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] interactive loop
I think readline() will do what you want. It can display a message and take user input, assigning it to a character value so you might need as.numeric() Michael On May 2, 2012, at 12:08 PM, Ondřej Mikula onmik...@gmail.com wrote: Dear R-helpers, I have a number of point configurations representing skull shapes, but some of them contain superfluous points. I want to write a loop in which each configuration is plotted and I am asked to write the numbers of points that are superfluous. However, I don't know how to introduce this interactive element. Would you give me an advice? Best regards Ondřej Mikula -- Ondřej Mikula Institute of Animal Physiology and Genetics Academy of Sciences of the Czech Republic Veveri 97, 60200 Brno, Czech Republic Institute of Vertebrate Biology Academy of Sciences of the Czech Republic Studenec 122, 67502 Konesin, Czech Republic __ 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] rgl.Sweave not producing transparency in pdf plots with alpha
On 02/05/2012 11:00 AM, Alexander Shenkin wrote: Hi Folks, I'm trying to get rgl.Sweave to produce plots with transparency. However, it just seems to produce opaque plots when pdf is the output type. Perhaps this is a known issue? I'll just use .png in the meantime, but wanted to see about this, as I didn't see it in the documentation (though it's possible I missed it). That uses the rgl.postscript() function, which uses the GL2PS library to convert to PDF. It may be that it doesn't support transparency in your scene. Or perhaps it just hasn't been turned on: GL2PS didn't support transparency when rgl.postscript was written. Duncan Murdoch Thanks, Allie \documentclass{article} \title {rgl test} \usepackage{Sweave} \begin {document} This is a test of rgl.sweave's alpha capability. \begin{figure} % uncomment line below for png output (correct transparency) %echo=FALSE, grdevice=rgl.Sweave, fig=TRUE, width=5, height=5, resolution=100= echo=FALSE, grdevice=rgl.Sweave, fig=TRUE, width=5, height=5, resolution=100, outputtype=pdf, pdf=TRUE= library(rgl) data(volcano) z- 2 * volcano# Exaggerate the relief x- 10 * (1:nrow(z)) # 10 meter spacing (S to N) y- 10 * (1:ncol(z)) # 10 meter spacing (E to W) zlim- range(y) zlen- zlim[2] - zlim[1] + 1 colorlut- terrain.colors(zlen) # height color lookup table col- colorlut[ z-zlim[1]+1 ] # assign colors to heights for each point #open3d() surface3d(x, y, z, color=col, back=lines, alpha=0.75) @ \end{figure} \end{document} __ 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] interactive loop
You might start with par(ask=TRUE) and identify(). A reproducible example might get you actual code. Also, how do you know they're superfluous? Perhaps that knowledge can be used to automate identification. Sarah On Wed, May 2, 2012 at 12:08 PM, Ondřej Mikula onmik...@gmail.com wrote: Dear R-helpers, I have a number of point configurations representing skull shapes, but some of them contain superfluous points. I want to write a loop in which each configuration is plotted and I am asked to write the numbers of points that are superfluous. However, I don't know how to introduce this interactive element. Would you give me an advice? Best regards Ondřej Mikula -- -- Sarah Goslee http://www.functionaldiversity.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] Statistical test for predictor selection
Hi, In a data I have two predictors and one response variable. The response variable is categorical and fixed. Now I want to choose which predictor would better predict the response variable. Is there a statistical test for that? Best, Jing -- Jing Tang, PhD Senior Researcher Institute for Molecular Medicine Finland (FIMM) FI-00014 University of Helsinki Finland [[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] Problems accessing environment() in function
On 01.05.2012 19:57, Heiko Neuhaus wrote: Hi all, I am trying to create a list of all variable/value combinations in environment(). When a function with unset arguments is called, the method I have been using fails with a missing argument error. However it should be possible to simply skip these missing objects in the generation of the list? Could anyone recommend me a better way (that does not use a slow for/eval-combination) to achieve the desired effect? You can easily reproduce my problem using this code: -- test1 - function(a, b, c) { x - as.list(environment()) print (hi from test1!) test2(a = a, b = b, c = c) You are rying to pass a, b, c here and hence R tries to insert those into the environment of test2 once it is called, you have not passed arguments to your test1 call. Uwe Ligges } test2 - function(a, b, c) { # PROBLEM: Why can't I get a list as in test1() here? x - as.list(environment()) print (hi from test2!) } test1() -- I want my list x in test2() to work behave just like x in test1(). (In this example the correct list in test2() would be empty). Thanks a lot for your time. Best wishes, Heiko Neuhaus __ 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] interactive loop
And now we have two entirely different interpretations of the question. I think Ondřej needs to provide a more detailed explanation of the problem and intended result. Sarah On Wed, May 2, 2012 at 12:23 PM, R. Michael Weylandt michael.weyla...@gmail.com michael.weyla...@gmail.com wrote: I think readline() will do what you want. It can display a message and take user input, assigning it to a character value so you might need as.numeric() Michael On May 2, 2012, at 12:08 PM, Ondřej Mikula onmik...@gmail.com wrote: Dear R-helpers, I have a number of point configurations representing skull shapes, but some of them contain superfluous points. I want to write a loop in which each configuration is plotted and I am asked to write the numbers of points that are superfluous. However, I don't know how to introduce this interactive element. Would you give me an advice? Best regards Ondřej Mikula -- Sarah Goslee http://www.functionaldiversity.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.
Re: [R] rgl.Sweave not producing transparency in pdf plots with alpha
On 02/05/2012 12:26 PM, Duncan Murdoch wrote: On 02/05/2012 11:00 AM, Alexander Shenkin wrote: Hi Folks, I'm trying to get rgl.Sweave to produce plots with transparency. However, it just seems to produce opaque plots when pdf is the output type. Perhaps this is a known issue? I'll just use .png in the meantime, but wanted to see about this, as I didn't see it in the documentation (though it's possible I missed it). That uses the rgl.postscript() function, which uses the GL2PS library to convert to PDF. It may be that it doesn't support transparency in your scene. Or perhaps it just hasn't been turned on: GL2PS didn't support transparency when rgl.postscript was written. I just took a look: transparency is turned off, and when it's turned on, it doesn't look very good. It's possible that there are tuning parameters that could make it look good, but I don't know what they are. Duncan Murdoch Duncan Murdoch Thanks, Allie \documentclass{article} \title {rgl test} \usepackage{Sweave} \begin {document} This is a test of rgl.sweave's alpha capability. \begin{figure} % uncomment line below for png output (correct transparency) %echo=FALSE, grdevice=rgl.Sweave, fig=TRUE, width=5, height=5, resolution=100= echo=FALSE, grdevice=rgl.Sweave, fig=TRUE, width=5, height=5, resolution=100, outputtype=pdf, pdf=TRUE= library(rgl) data(volcano) z- 2 * volcano# Exaggerate the relief x- 10 * (1:nrow(z)) # 10 meter spacing (S to N) y- 10 * (1:ncol(z)) # 10 meter spacing (E to W) zlim- range(y) zlen- zlim[2] - zlim[1] + 1 colorlut- terrain.colors(zlen) # height color lookup table col- colorlut[ z-zlim[1]+1 ] # assign colors to heights for each point #open3d() surface3d(x, y, z, color=col, back=lines, alpha=0.75) @ \end{figure} \end{document} __ 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] rgl.Sweave not producing transparency in pdf plots with alpha
On 5/2/2012 11:40 AM, Duncan Murdoch wrote: On 02/05/2012 12:26 PM, Duncan Murdoch wrote: On 02/05/2012 11:00 AM, Alexander Shenkin wrote: Hi Folks, I'm trying to get rgl.Sweave to produce plots with transparency. However, it just seems to produce opaque plots when pdf is the output type. Perhaps this is a known issue? I'll just use .png in the meantime, but wanted to see about this, as I didn't see it in the documentation (though it's possible I missed it). That uses the rgl.postscript() function, which uses the GL2PS library to convert to PDF. It may be that it doesn't support transparency in your scene. Or perhaps it just hasn't been turned on: GL2PS didn't support transparency when rgl.postscript was written. I just took a look: transparency is turned off, and when it's turned on, it doesn't look very good. It's possible that there are tuning parameters that could make it look good, but I don't know what they are. Duncan Murdoch Thanks Duncan, I'll just stick with png for now then. Duncan Murdoch Thanks, Allie \documentclass{article} \title {rgl test} \usepackage{Sweave} \begin {document} This is a test of rgl.sweave's alpha capability. \begin{figure} % uncomment line below for png output (correct transparency) %echo=FALSE, grdevice=rgl.Sweave, fig=TRUE, width=5, height=5, resolution=100= echo=FALSE, grdevice=rgl.Sweave, fig=TRUE, width=5, height=5, resolution=100, outputtype=pdf, pdf=TRUE= library(rgl) data(volcano) z- 2 * volcano# Exaggerate the relief x- 10 * (1:nrow(z)) # 10 meter spacing (S to N) y- 10 * (1:ncol(z)) # 10 meter spacing (E to W) zlim- range(y) zlen- zlim[2] - zlim[1] + 1 colorlut- terrain.colors(zlen) # height color lookup table col- colorlut[ z-zlim[1]+1 ] # assign colors to heights for each point #open3d() surface3d(x, y, z, color=col, back=lines, alpha=0.75) @ \end{figure} \end{document} __ 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] please help me
On 02.05.2012 02:55, Ulfa Hasanah wrote: hi all,can you help me? index moran is very difficut for me, i have data n neighbor as enclosure: please help me to make the program for find index moran value each variabel,...thank very much Which translates to: please help me, and note that - I have to do some homework - I do not want to read the posting guide - I do not want to read a stats textbook about the methods I have to apply - I do not want to read An Introduction to R - I do not want to fix the broken shift key of my keyboard - I am too lazy to type what I did so far Now, I think we can assume that it is impossible to help you with a simple e-mail response. Please ask your supervisor. Uwe Ligges __ 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] convert numbers into dates and time
On 02.05.2012 11:19, mpostje wrote: Hi I've been trying to convert numbers from an online temperature database into dates and time that R recognizes. the problem is that the database has put a T between the numbers and R will not accept any conversions. this is the format that it's in now 1981-01-02T08:00 strptime(1981-01-02T08:00, format=%Y-%m-%dT%H:%M) seems to work for me. Uwe Ligges can anyone help? cheers! -- View this message in context: http://r.789695.n4.nabble.com/convert-numbers-into-dates-and-time-tp4602708.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] selection by two unique variables
try this: x - read.table(text = id wtdt wt lastpk + + 64050256 2010-09-18 275 2010-09-16 + + 64050256 2010-09-19 277 2010-09-18 + + 64050256 2010-09-20 272 2010-09-18 + + 64050256 2010-09-21 277 2010-09-18, as.is = TRUE, header = TRUE) first - lapply(split(x, list(x$id, x$lastpk), drop = TRUE), function(a){ + a[1,, drop = FALSE] + }) do.call(rbind, first) id wtdt wt lastpk 64050256.2010-09-16 64050256 2010-09-18 275 2010-09-16 64050256.2010-09-18 64050256 2010-09-19 277 2010-09-18 On Wed, May 2, 2012 at 11:23 AM, Bert Gunter gunter.ber...@gene.com wrote: ?tapply ?with is also useful here as in (untested) with(yourdataframe, tapply(lastpk, id, unique)) -- Bert On Wed, May 2, 2012 at 7:58 AM, Ayyappa Chaturvedula ayyapp...@gmail.com wrote: Dear Group, I am working with a large dataset where I need to select for each unique id the the unique lastpk row. Here is a sample subject: id wtdt wt lastpk 64050256 2010-09-18 275 2010-09-16 64050256 2010-09-19 277 2010-09-18 64050256 2010-09-20 272 2010-09-18 64050256 2010-09-21 277 2010-09-18 I want the result as: id wtdt wt lastpk 64050256 2010-09-18 275 2010-09-16 64050256 2010-09-19 277 2010-09-18 I am using !(duplicated(data$id)) to select the first row but now I want to select the first row of the unique lastpk in each unique id. I appreciate your help on this. Regards, Ayyappa [[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. -- Bert Gunter Genentech Nonclinical Biostatistics Internal Contact Info: Phone: 467-7374 Website: http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm __ 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. -- Jim Holtman Data Munger Guru What is the problem that you are trying to solve? Tell me what you want to do, not how you want to do it. __ 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] Problems accessing environment() in function
Thanks a lot for your answer! -- test1 - function(a, b, c) { x - as.list(environment()) print (hi from test1!) test2(a = a, b = b, c = c) You are rying to pass a, b, c here and hence R tries to insert those into the environment of test2 once it is called, you have not passed arguments to your test1 call. Uwe Ligges I am aware that I am passing non existing arguments here, which is why my method of creating a list of the environment as.list(environment()) seems to fail in this case. What I need is a way to just skip non existing objects when I create my list. In my given example I was intending to receive an empty list, since no valid arguments were passed to test2(). In other words: I want a list containing all _existing_ variable/value combinations and just skip the missing ones. Thanks again for your time Best wishes, Heiko Neuhaus __ 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] strange differences in vector operation versus manual calculation
On Wed, May 02, 2012 at 11:42:27AM -0400, Rajarshi Guha wrote: Hi, I'm running a calculation in two ways. The first way is to employ vectors and evaluate a function in one go. The second way is to break down the function into pieces and combine the pieces to the final answer. Algebraically, they should give me the same result. But the final vector differs significantly. I must be missing something very obvious, but I just cannot see it xx - c(-9.56305825951348, -8.20220288142583, -6.84134750333818, -5.48049212525052, -4.11963674716287) params - structure(c(-7.9292094394, 4.9549173134, 4.738588416, 101.5743644892 ), .Names = c(LOG_AC50, HILL_COEF, INF_ACTIVITY, ZERO_ACTIVITY )) yy - params[4] + (params[3] - params[4])/(1 + 10^(params[1]-xx)^params[2]) t1 - 10^(params[1]-xx) t2 - params[3] - params[4] t3 - (1+t1)^params[2] t4 - t2/t3; t5 - params[4] + t4 I would've expected yy and t5 to be the same; yet they are not Hi. The difference is caused by different placement of parenthesis. Replacing (1 + 10^(params[1]-xx)^params[2]) by (1 + 10^(params[1]-xx))^params[2] yields [1] 101.574364 101.057295 35.949148 6.428122 4.812942 which is equal to t5. Petr Savicky. __ 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] Forestplot question
Hi, I'm trying to build a Forest Plot using the second and fourth columns in the table (test.csv) below. My code is the following: curated - data.frame(test.csv) tmp - curated$coef tmp1 - curated$se_coef plt - metaplot(tmp, tmp1, xlim = c(-.45, .45)) I keep getting the following error at the last line and am not sure why: Error in if (is.na(lower[i] + upper[i])) next : argument is of length zero For the metaplot() function, the help page looks like at a minimum I need to input the point estimates from the studies as well as the standard errors of the point estimates as parameters (an earlier error occurred telling me I needed xlim as well). I would greatly appreciate any clarification anyone can provide. IDs coef exp_coef se_coef z Pr(|z|) 1 -0.203063307 0.816226567 0.082936899 -2.448407282 0.014348936 2 0 1 0 NA NA 3 -0.193553687 0.824025596 0.114027975 -1.697422824 0.089616751 4 -0.032175939 0.968336199 0.239318707 -0.134448074 0.893048269 5 -0.20511693 0.814552066 0.121275633 -1.691328457 0.090774088 6 -0.201827336 0.817236023 0.154827334 -1.30356398 0.192382289 7 -0.439783875 0.644175628 0.105856496 -4.154528917 3.26E-05 8 -0.262717505 0.768959094 0.144606241 -1.816778471 0.069251041 9 -0.208431217 0.811856875 0.225960968 -0.922421329 0.356308848 [[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] Problems accessing environment() in function
On 02/05/2012 12:59 PM, Heiko Neuhaus wrote: Thanks a lot for your answer! -- test1- function(a, b, c) { x- as.list(environment()) print (hi from test1!) test2(a = a, b = b, c = c) You are rying to pass a, b, c here and hence R tries to insert those into the environment of test2 once it is called, you have not passed arguments to your test1 call. Uwe Ligges I am aware that I am passing non existing arguments here, which is why my method of creating a list of the environment as.list(environment()) seems to fail in this case. What I need is a way to just skip non existing objects when I create my list. In my given example I was intending to receive an empty list, since no valid arguments were passed to test2(). In other words: I want a list containing all _existing_ variable/value combinations and just skip the missing ones. That's hard to do, because missing arguments exist, they just have a special value to signal that they were missing. The missing() function tests for that value, but it is picky about its arguments. So if you want to do all of this in R you probably need some tricky programming, like this: f - function(a,b,c) { names - ls(environment()) # get all the names result - list() for (n in names) { if (!do.call(missing, list(as.name(n result[n] - get(n) } result } If you put the ls() call later, you'll pick up other local variables (names, result, n) as well. 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] adding a caption to a mosaic plot?
Dear all: Is there a way to add text to the margins or outer margins of a mosaic plot using the vcd package? I understand the margins argument to mosaic, but I don't know how to add text to that. I'd like to add a caption to a plot. If possible, I'd like to know how to set the font and size for that function as well. My plot looks roughly as below. Thank you for your time! Simon J. Kiss mydat-data.frame(gender=factor(rbinom(100, 1, 0.5), labels=c('female', 'male')), hair=factor(rbinom(100, 1, 0.5), labels=c('blonde', 'black'))) mosaic_1-table(mydat) mosaic(mosaic_1, gp=shading_hsv, main='my title', pop=FALSE, split_vertical=FALSE, margins=c(4.1, 2.1, 8, 5.1), labeling_args=list(rot_labels=c(left=0), offset_labels=c(left=3), gp_main=gpar(cex=2), offset_varnames=c(left=5.5), gp_labels=gpar(cex=1.5), gp_varnames=gpar(cex=1.5), labeling_values=c('observed'))) labeling_cells(text=round(prop.table(mosaic_1, 1)*100), gp_text=gpar(ces=2), clip=FALSE)(mosaic_1) * Simon J. Kiss, PhD Assistant Professor, Wilfrid Laurier University 73 George Street Brantford, Ontario, Canada N3T 2C9 Cell: +1 905 746 7606 __ 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 'nls' fitting logistic model (5PL)
Dear R-Helpers, I'm working with immunoassay data and 5PL logistic model. I wanted to experiment with different forms of weighting and parameter selection, which is not possible in instrument software, so I turned to R. I am using R 2.14.2 under Win7 64bit, and the 'nls' library to fit the model - I started with the same model and weighting type (1/y) as in the instrument to see if I'll get similar results. However, in some instances I don't get any results - just errors. Here is an example calibration data, representative of my experiment. Instrument soft had no problem fitting it: x - structure(list(SPL = structure(c(1L, 1L, 2L, 2L, 3L, 3L, 4L, 4L, 5L, 5L, 6L, 6L, 7L, 7L), .Label = c(St1, St2, St3, St4, St5, St6, St7), class = factor), MFI = c(10755.5, 9839, 5142.5, 4857, 1510.5, 1505, 502.5, 451, 215, 195.5, 58, 57, 15, 15), nom = c(206, 206, 125, 125, 68, 68, 38, 38, 24, 24, 13, 13, 6.5, 6.5), weights = c(0.0013946353028683, 0.00152454517735542, 0.00291686922702965, 0.00308832612723904, 0.0099304865938431, 0.00996677740863787, 0.0298507462686567, 0.0332594235033259, 0.0697674418604651, 0.0767263427109974, 0.258620689655172, 0.263157894736842, 1, 1)), .Names = c(SPL, MFI, nom, weights), row.names = c(NA, -14L), class = data.frame) And here is the nls fit: fit - nls(MFI~a + b/((1+(nom/c)^d)^f), data=x, weights=x$weights, start=c(a=100, b=1, c=100, d=-1, f=1)) I've tried every possible combination of starting values, including the values fitted by the instrument soft - to no avail. I've probably seen all possible error messages from 'nls' trying to fit this. If anyone has an idea why it's not working - let me know. Best regards, -- Michal J. Figurski, PhD HUP, Pathology Laboratory Medicine Biomarker Research Laboratory 3400 Spruce St. 7 Maloney S Philadelphia, PA 19104 tel. (215) 662-3413 __ 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 'nls' fitting logistic model (5PL)
Plot the data. You're clearly overfitting. (If you don't know what this means or why it causes the problems you see, try a statistical help list or consult your local statistician). -- Bert On Wed, May 2, 2012 at 12:32 PM, Michal Figurski figur...@mail.med.upenn.edu wrote: Dear R-Helpers, I'm working with immunoassay data and 5PL logistic model. I wanted to experiment with different forms of weighting and parameter selection, which is not possible in instrument software, so I turned to R. I am using R 2.14.2 under Win7 64bit, and the 'nls' library to fit the model - I started with the same model and weighting type (1/y) as in the instrument to see if I'll get similar results. However, in some instances I don't get any results - just errors. Here is an example calibration data, representative of my experiment. Instrument soft had no problem fitting it: x - structure(list(SPL = structure(c(1L, 1L, 2L, 2L, 3L, 3L, 4L, 4L, 5L, 5L, 6L, 6L, 7L, 7L), .Label = c(St1, St2, St3, St4, St5, St6, St7), class = factor), MFI = c(10755.5, 9839, 5142.5, 4857, 1510.5, 1505, 502.5, 451, 215, 195.5, 58, 57, 15, 15), nom = c(206, 206, 125, 125, 68, 68, 38, 38, 24, 24, 13, 13, 6.5, 6.5), weights = c(0.0013946353028683, 0.00152454517735542, 0.00291686922702965, 0.00308832612723904, 0.0099304865938431, 0.00996677740863787, 0.0298507462686567, 0.0332594235033259, 0.0697674418604651, 0.0767263427109974, 0.258620689655172, 0.263157894736842, 1, 1)), .Names = c(SPL, MFI, nom, weights), row.names = c(NA, -14L), class = data.frame) And here is the nls fit: fit - nls(MFI~a + b/((1+(nom/c)^d)^f), data=x, weights=x$weights, start=c(a=100, b=1, c=100, d=-1, f=1)) I've tried every possible combination of starting values, including the values fitted by the instrument soft - to no avail. I've probably seen all possible error messages from 'nls' trying to fit this. If anyone has an idea why it's not working - let me know. Best regards, -- Michal J. Figurski, PhD HUP, Pathology Laboratory Medicine Biomarker Research Laboratory 3400 Spruce St. 7 Maloney S Philadelphia, PA 19104 tel. (215) 662-3413 __ 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. -- Bert Gunter Genentech Nonclinical Biostatistics Internal Contact Info: Phone: 467-7374 Website: http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm __ 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] Problems accessing environment() in function
Thank you very much for your suggestion. f - function(a,b,c) { names - ls(environment()) # get all the names result - list() for (n in names) { if (!do.call(missing, list(as.name(n result[n] - get(n) } result } I have already figured out a very similar solution using for/eval that basically does the same. I was hoping that I would somehow could get around the ugly loop using a more elegant approach. The loop should have a negative impact on performance since my function is using a lot of parameters. I was hoping, that there was some flag to tell the as.list function to ignore non existing objects. If that is not possible I will have to accept this. If you put the ls() call later, you'll pick up other local variables (names, result, n) as well. Of course. That is why I call it at the very first line of my function. Thanks again! Heiko Neuhaus __ 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] Quickest way to make a large empty file on disk?
R-helpers: What would be the absolute fastest way to make a large empty file (e.g. filled with all zeroes) on disk, given a byte size and a given number number of empty values. I know I can use writeBin, but the object in this case may be far too large to store in main memory. I'm asking because I'm going to use this file in conjunction with mmap to do parallel writes to this file. Say, I want to create a blank file of 10,000 floating point numbers. Thanks! --j -- Jonathan A. Greenberg, PhD Assistant Professor Department of Geography and Geographic Information Science University of Illinois at Urbana-Champaign 607 South Mathews Avenue, MC 150 Urbana, IL 61801 Phone: 415-763-5476 AIM: jgrn307, MSN: jgrn...@hotmail.com, Gchat: jgrn307, Skype: jgrn3007 http://www.geog.illinois.edu/people/JonathanGreenberg.html [[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] [R-sig-hpc] Quickest way to make a large empty file on disk?
Look at the man page for dd (assuming you are on *nix) A quick google will get you a command to try. I'm not at my desk or I would as well. Jeff Jeffrey Ryan|Founder|jeffrey.r...@lemnica.com www.lemnica.com On May 2, 2012, at 5:23 PM, Jonathan Greenberg j...@illinois.edu wrote: R-helpers: What would be the absolute fastest way to make a large empty file (e.g. filled with all zeroes) on disk, given a byte size and a given number number of empty values. I know I can use writeBin, but the object in this case may be far too large to store in main memory. I'm asking because I'm going to use this file in conjunction with mmap to do parallel writes to this file. Say, I want to create a blank file of 10,000 floating point numbers. Thanks! --j -- Jonathan A. Greenberg, PhD Assistant Professor Department of Geography and Geographic Information Science University of Illinois at Urbana-Champaign 607 South Mathews Avenue, MC 150 Urbana, IL 61801 Phone: 415-763-5476 AIM: jgrn307, MSN: jgrn...@hotmail.com, Gchat: jgrn307, Skype: jgrn3007 http://www.geog.illinois.edu/people/JonathanGreenberg.html [[alternative HTML version deleted]] ___ R-sig-hpc mailing list r-sig-...@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-hpc __ 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] Quickest way to make a large empty file on disk?
An R solution is: allocateFile - function(pathname, nbrOfBytes) { con - file(pathname, open=wb); on.exit(close(con)); seek(con, where=nbrOfBytes-1L, origin=start, rw=write); writeBin(as.raw(0), con=con); invisible(pathname); } # allocateFile() allocateFile(foo.bin, nbrOfBytes=985403) file.info(foo.bin)$size [1] 985403 Note sure if it works on all OSes/file systems. /Henrik On Wed, May 2, 2012 at 3:23 PM, Jonathan Greenberg j...@illinois.edu wrote: R-helpers: What would be the absolute fastest way to make a large empty file (e.g. filled with all zeroes) on disk, given a byte size and a given number number of empty values. I know I can use writeBin, but the object in this case may be far too large to store in main memory. I'm asking because I'm going to use this file in conjunction with mmap to do parallel writes to this file. Say, I want to create a blank file of 10,000 floating point numbers. Thanks! --j -- Jonathan A. Greenberg, PhD Assistant Professor Department of Geography and Geographic Information Science University of Illinois at Urbana-Champaign 607 South Mathews Avenue, MC 150 Urbana, IL 61801 Phone: 415-763-5476 AIM: jgrn307, MSN: jgrn...@hotmail.com, Gchat: jgrn307, Skype: jgrn3007 http://www.geog.illinois.edu/people/JonathanGreenberg.html [[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] Problems accessing environment() in function
On 12-05-02 5:20 PM, Heiko Neuhaus wrote: Thank you very much for your suggestion. f- function(a,b,c) { names- ls(environment()) # get all the names result- list() for (n in names) { if (!do.call(missing, list(as.name(n result[n]- get(n) } result } I have already figured out a very similar solution using for/eval that basically does the same. I was hoping that I would somehow could get around the ugly loop using a more elegant approach. What you're doing looks ugly, so don't expect an elegant solution. (I say it's ugly because you're redefining terms like exists.) If you work with the language things will look nicer. Duncan Murdoch The loop should have a negative impact on performance since my function is using a lot of parameters. I was hoping, that there was some flag to tell the as.list function to ignore non existing objects. If that is not possible I will have to accept this. If you put the ls() call later, you'll pick up other local variables (names, result, n) as well. Of course. That is why I call it at the very first line of my function. __ 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] [R-sig-hpc] Quickest way to make a large empty file on disk?
Something like: http://markus.revti.com/2007/06/creating-empty-file-with-specified-size/ Is one way I know of. Jeff Jeffrey Ryan|Founder|jeffrey.r...@lemnica.com www.lemnica.com On May 2, 2012, at 5:23 PM, Jonathan Greenberg j...@illinois.edu wrote: R-helpers: What would be the absolute fastest way to make a large empty file (e.g. filled with all zeroes) on disk, given a byte size and a given number number of empty values. I know I can use writeBin, but the object in this case may be far too large to store in main memory. I'm asking because I'm going to use this file in conjunction with mmap to do parallel writes to this file. Say, I want to create a blank file of 10,000 floating point numbers. Thanks! --j -- Jonathan A. Greenberg, PhD Assistant Professor Department of Geography and Geographic Information Science University of Illinois at Urbana-Champaign 607 South Mathews Avenue, MC 150 Urbana, IL 61801 Phone: 415-763-5476 AIM: jgrn307, MSN: jgrn...@hotmail.com, Gchat: jgrn307, Skype: jgrn3007 http://www.geog.illinois.edu/people/JonathanGreenberg.html [[alternative HTML version deleted]] ___ R-sig-hpc mailing list r-sig-...@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-hpc __ 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] Forestplot question
It works for me with your data: dat-read.table(/tmp/foo.txt,header=TRUE) metaplot(a$coef,a$se_coef) It has boxes of size zero for the point estimates, but that's because you give the standard error as zero for the second estimate, which implies all the other boxes should be infinitely smaller. Presumably the std error isn't actually zero. -thomas On Thu, May 3, 2012 at 5:39 AM, Ben Ganzfried benganzfr...@post.harvard.edu wrote: Hi, I'm trying to build a Forest Plot using the second and fourth columns in the table (test.csv) below. My code is the following: curated - data.frame(test.csv) tmp - curated$coef tmp1 - curated$se_coef plt - metaplot(tmp, tmp1, xlim = c(-.45, .45)) I keep getting the following error at the last line and am not sure why: Error in if (is.na(lower[i] + upper[i])) next : argument is of length zero For the metaplot() function, the help page looks like at a minimum I need to input the point estimates from the studies as well as the standard errors of the point estimates as parameters (an earlier error occurred telling me I needed xlim as well). I would greatly appreciate any clarification anyone can provide. IDs coef exp_coef se_coef z Pr(|z|) 1 -0.203063307 0.816226567 0.082936899 -2.448407282 0.014348936 2 0 1 0 NA NA 3 -0.193553687 0.824025596 0.114027975 -1.697422824 0.089616751 4 -0.032175939 0.968336199 0.239318707 -0.134448074 0.893048269 5 -0.20511693 0.814552066 0.121275633 -1.691328457 0.090774088 6 -0.201827336 0.817236023 0.154827334 -1.30356398 0.192382289 7 -0.439783875 0.644175628 0.105856496 -4.154528917 3.26E-05 8 -0.262717505 0.768959094 0.144606241 -1.816778471 0.069251041 9 -0.208431217 0.811856875 0.225960968 -0.922421329 0.356308848 [[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. -- Thomas Lumley Professor of Biostatistics University of Auckland __ 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 in La.svd Lapack routine 'dgesdd'
Addendum to my first post: Since I wish to understand what plm does to my data, I tried to manually calculate the demeaned values and use OLS. See below how far I got with the Grunfeld data; formula's are based on Greene's Econometric Analysis. Obviously, I am missing at least one important step as my results differ from both the plm and the LSDV estimations. Transferring the model to my original dataset, I i) also get different results for the lm vs. the plm models, however with the manually demeaned dataset, I do not end up with incredibly small standard deviations in the demeaned values. That is, the step that I am missing when reproducing the plm results is highly probable to cause the error in my analysis. ### library(plm) library(lmtest) data(Grunfeld) head(Grunfeld) pdata-pdata.frame(Grunfeld,index=c(firm,year)) head(pdata) fm-inv~value+capital mod-plm(fm, pdata, effect=twoways, model=within) y-Grunfeld$inv x1-Grunfeld$value x2-Grunfeld$capital y_i-c() x1_i-c() x2_i-c() for (i in unique(Grunfeld$firm)){ y_i-c(y_i,rep(mean(Grunfeld$inv[Grunfeld$firm==i],na.rm=TRUE),nrow(Grunfeld))) x1_i-c(x1_i,rep(mean(Grunfeld$value[Grunfeld$firm==i],na.rm=TRUE),nrow(Grunfeld))) x2_i-c(x2_i,rep(mean(Grunfeld$capital[Grunfeld$firm==i],na.rm=TRUE),nrow(Grunfeld))) } y_t-rep(NA,nrow(Grunfeld)) x1_t-rep(NA,nrow(Grunfeld)) x2_t-rep(NA,nrow(Grunfeld)) for (t in unique(Grunfeld$year)){ y_t[Grunfeld$year==t]-rep(mean(Grunfeld$inv[Grunfeld$year==t],na.rm=TRUE),sum(Grunfeld$year==t)) x1_t[Grunfeld$year==t]-rep(mean(Grunfeld$value[Grunfeld$year==t],na.rm=TRUE),sum(Grunfeld$year==t)) x2_t[Grunfeld$year==t]-rep(mean(Grunfeld$capital[Grunfeld$year==t],na.rm=TRUE),sum(Grunfeld$year==t)) } y_it-rep(mean(Grunfeld$inv,na.rm=TRUE),nrow(Grunfeld)) x1_it-rep(mean(Grunfeld$value,na.rm=TRUE),nrow(Grunfeld)) x2_it-rep(mean(Grunfeld$capital,na.rm=TRUE),nrow(Grunfeld)) y_star-y-y_i-y_t+y_it x1_star-x1-x1_i-x1_t+x1_it x2_star-x2-x2_i-x2_t+x2_it mod_lm-lm(y_star~x1_star+x2_star-1,na.action=na.omit) mod_dumm-lm(Grunfeld$inv~Grunfeld$value+Grunfeld$capital+as.factor(Grunfeld$year)+as.factor(Grunfeld$firm)-1,na.action=na.omit) coeftest(mod) coeftest(mod_lm) coeftest(mod_dumm) ## Again, any help is highly appreciated. Best wishes, Philipp - EBS Universitaet fuer Wirtschaft und Recht FARE Department Wiesbaden/ Germany http://www.ebs.edu/index.php?id=finaccL=0 -- View this message in context: http://r.789695.n4.nabble.com/error-in-La-svd-Lapack-routine-dgesdd-tp2125052p4604714.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Numeric data not numeric in .csv file
Thanks everyone for your helpful responses. I looked at the csv file in a text editor and saw no spaces or non-numerical characters (other than periods as decimals) outside of the header. str() says me that the variables are either num or int. David was spot-on; I was trying storage.mode(~miles) [1] language instead of storage.mode(hikes$miles) [1] double The fault was in my grasp of R's syntax, not the data. Thanks! On Wed, May 2, 2012 at 10:09 AM, David Winsemius dwinsem...@comcast.netwrote: On May 1, 2012, at 8:47 PM, Eve Proper wrote: I am a raw novice to R, playing around with a mini .csv dataset created in Excel. I can read it in and the data looks OK in Excel and upon initial inspection in R: hikes - read.csv(/Users/eproper/**Desktop/hikes.csv, header=TRUE) print(hikes) does exactly what it is supposed to do. Two of the variables are genuine strings, but the others ought to be numeric, and R will calculate their min, max etc. However, is.numeric returns FALSE for all of them; How did you do this? What code did you use? It should have been: lapply(hikes, is.numeric) storage.mode returns language. Well, that suggests that you were trying to use unquoted variable names without the data objects name. Did you use attach() on the basis of some misguided instructions? as.numeric returns Error: 'pairlist' object cannot be coerced to type 'double'. In what I suspect is a related problem, any command that calls for a variable name requires an initial ~ to work. That is, instead of plot(miles) I have to use plot(~miles). As I said, you are not correctly referencing column names within data objects. No doubt there is some very elementary mistake I am making, but I can't figure it out. Any help would be appreciated. http://theturducken.blogspot.**com/ http://theturducken.blogspot.com/ [[alternative HTML version deleted]] And you should read the Posting Guide and correct your posting format. __** R-help@r-project.org mailing list https://stat.ethz.ch/mailman/**listinfo/r-helphttps://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/** posting-guide.html http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. David Winsemius, MD Heritage Laboratories West Hartford, CT [[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] is there a way of identifying batch mode running?
Hello list Is there a way of identifying from within R whether a script has been source(d) from Rgui.exe or via Rscript.exe in batch mode? For the code I have I use the commandArgs() function to pick up command line args when running in batch mode via Rscript.exe However I like to get the code working manually first using source(MyRCode.r) I'd like to be able to put something at the top of the file that discriminates between the two running modes eg #Rscript.exe --slave -e source('MyRCode.r') some_data_file.txt if(batchmode = TRUE){ #get arguments for script from command line foo - commandArgs() #where commandArgs() returns some_data_file.txt } if(batchmode == FALSE){ #no command line usage so need to manually supply starting arguments for script foo - some_data_file.txt } [[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] is there a way of identifying batch mode running?
interactive() does not do exactly what you ask for, but may be close enough. It returns FALSE when run from Rscript and TRUE from R when you have not redirected standard input. Bill Dunlap Spotfire, TIBCO Software wdunlap tibco.com -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of paul.rusto...@csiro.au Sent: Wednesday, May 02, 2012 5:10 PM To: r-help@r-project.org Subject: [R] is there a way of identifying batch mode running? Hello list Is there a way of identifying from within R whether a script has been source(d) from Rgui.exe or via Rscript.exe in batch mode? For the code I have I use the commandArgs() function to pick up command line args when running in batch mode via Rscript.exe However I like to get the code working manually first using source(MyRCode.r) I'd like to be able to put something at the top of the file that discriminates between the two running modes eg #Rscript.exe --slave -e source('MyRCode.r') some_data_file.txt if(batchmode = TRUE){ #get arguments for script from command line foo - commandArgs() #where commandArgs() returns some_data_file.txt } if(batchmode == FALSE){ #no command line usage so need to manually supply starting arguments for script foo - some_data_file.txt } [[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] [R-sig-hpc] Quickest way to make a large empty file on disk?
On May 2, 2012, at 6:23 PM, Jonathan Greenberg wrote: R-helpers: What would be the absolute fastest way to make a large empty file (e.g. filled with all zeroes) on disk, given a byte size and a given number number of empty values. I know I can use writeBin, but the object in this case may be far too large to store in main memory. I'm asking because I'm going to use this file in conjunction with mmap to do parallel writes to this file. Say, I want to create a blank file of 10,000 floating point numbers. The most trivial way is to simply seek to the end and write a byte: n=10 f=file(foo,wb) seek(f,n-1) [1] 0 writeBin(raw(1),f) close(f) file.info(foo)$size [1] 1e+05 Cheers, Simon Thanks! --j -- Jonathan A. Greenberg, PhD Assistant Professor Department of Geography and Geographic Information Science University of Illinois at Urbana-Champaign 607 South Mathews Avenue, MC 150 Urbana, IL 61801 Phone: 415-763-5476 AIM: jgrn307, MSN: jgrn...@hotmail.com, Gchat: jgrn307, Skype: jgrn3007 http://www.geog.illinois.edu/people/JonathanGreenberg.html [[alternative HTML version deleted]] ___ R-sig-hpc mailing list r-sig-...@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-hpc __ 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] [R-sig-hpc] Quickest way to make a large empty file on disk?
On most UNIX systems this will leave a large unallocated virtual hole in the file. If you are not bothered by spreading the allocation task out over the program execution interval, this won't matter and will probably give the best performance. However, if you wanted to benchmark your algorithms without the erratic filesystem updates mixed in, then you need to write all of those zeroes. For that to work most efficiently, write data in large blocks, and if possible bypass the C standard library. --- Jeff NewmillerThe . . Go Live... DCN:jdnew...@dcn.davis.ca.usBasics: ##.#. ##.#. Live Go... Live: OO#.. Dead: OO#.. Playing Research Engineer (Solar/BatteriesO.O#. #.O#. with /Software/Embedded Controllers) .OO#. .OO#. rocks...1k --- Sent from my phone. Please excuse my brevity. Simon Urbanek simon.urba...@r-project.org wrote: On May 2, 2012, at 6:23 PM, Jonathan Greenberg wrote: R-helpers: What would be the absolute fastest way to make a large empty file (e.g. filled with all zeroes) on disk, given a byte size and a given number number of empty values. I know I can use writeBin, but the object in this case may be far too large to store in main memory. I'm asking because I'm going to use this file in conjunction with mmap to do parallel writes to this file. Say, I want to create a blank file of 10,000 floating point numbers. The most trivial way is to simply seek to the end and write a byte: n=10 f=file(foo,wb) seek(f,n-1) [1] 0 writeBin(raw(1),f) close(f) file.info(foo)$size [1] 1e+05 Cheers, Simon Thanks! --j -- Jonathan A. Greenberg, PhD Assistant Professor Department of Geography and Geographic Information Science University of Illinois at Urbana-Champaign 607 South Mathews Avenue, MC 150 Urbana, IL 61801 Phone: 415-763-5476 AIM: jgrn307, MSN: jgrn...@hotmail.com, Gchat: jgrn307, Skype: jgrn3007 http://www.geog.illinois.edu/people/JonathanGreenberg.html [[alternative HTML version deleted]] ___ R-sig-hpc mailing list r-sig-...@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-hpc __ 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] scanning a data set for strings
Worked like a charm. Thanks for the help! It's really appreciated. -- View this message in context: http://r.789695.n4.nabble.com/scanning-a-data-set-for-strings-tp4602953p4603410.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] error fitting coxph model
Hi, I am using coxph from the survival package to fit a large model (100,000 observations, ~35 covariates) using both ridge regression (on binary covariates) and penalized splines (for continuous covariates). In fitting, I get a strange error: Error in if (abs((y[nx] - target)/(y[nx - 1] - target)) 0.6) doing.well - FALSE else doing.well - TRUE : missing value where TRUE/FALSE needed Unfortunately, I can't reproduce this error without handing over my entire dataset, but I thought it would be worth checking if anyone had any insight. I should note that the outcome that I'm using has almost everyone having an event (~98,000 events out of 100,000). I have fit other models like this with no problem, but on one particular dataset it fails. Thanks! Jessica Myers Instructor in Medicine Brigham and Women's Hospital The information in this e-mail is intended only for the ...{{dropped:7}} __ 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 can a function in R handle different types of input?
Hi, How can a function in R handle different types of input? I have written a function, which should calculate the slope from several 3-time-point measurements by linear regression 4 three-time-point-measurements: x-cbind(c(1,2,3,4),c(2,3,4,5),c(3,4,5,6)) time points: time-c(1,3,9) function for calculating the slope by linear regression: fit-function(xx,t){slope - coefficients(lm(log(xx) ~ 0 + t))[1] return(slope) } alpha-fit(x[1,],time) At the moment the function output 'alpha' is calculated for x(x1=1,x2=2,x3=3). I would like to get 'alphas' for all four rows of x without using a for-loop. If I use 'mapply', I get outputs to very entry of x (12 outputs) instead of four. Thank you very much in advance! Yor help is really appreciated! Stella -- View this message in context: http://r.789695.n4.nabble.com/How-can-a-function-in-R-handle-different-types-of-input-tp4603263.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] pick up the values
Hi, I have a list of data, e.g. r[[i]] r[[1]]= 1 2 1 6 5 5 5.5 3 r[[2]]= 46 35 78 35 … r[[500]]. In the first column, the selected values should like this: (the later value)-(the former value)=1 In the second column, the selected values should like this: (the former value)-(the later value)=1. The outputs are: For r[[1]] [1,1] 1, [3,1] 5, [1,2] 2 For r[[2]] [1,1] 4, [3,1] 7 [1,2] 6, [2,1] 5 … r[[500]]. I have no idea what kind of functions can be used in this process. Could you help me? Thank you very much. -- View this message in context: http://r.789695.n4.nabble.com/pick-up-the-values-tp4603277.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] date and time conversion
Hello, mpostje wrote Hi I've been trying to convert numbers from an online temperature database into dates and time that R recognizes. the problem is that the database has put a T between the numbers and R will not accept any conversions. this is the format that it's in now 1981-01-02T08:00 can anyone help? cheers! Try x - 1981-01-02T08:00 x.new - sub(T, , x) as.POSIXct(x.new) Hope this helps, Rui Barradas -- View this message in context: http://r.789695.n4.nabble.com/date-and-time-conversion-tp4602786p4603288.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] strange differences in vector operation versus manual calculation
Hello, I must be missing something very obvious, but I just cannot see it. The hardest to find errors. Wrong manual calculation in t1, powers have precedence right to left and before additions. t1b - 10^(params[1]-xx)^params[2] t3b - 1 + t1b t4b - t2/t3b t5b - params[4] + t4b all.equal(yy, t5b) TRUE Hope this helps, Rui Barradas -- View this message in context: http://r.789695.n4.nabble.com/strange-differences-in-vector-operation-versus-manual-calculation-tp4603600p4603707.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] Binary logistic regression with binary predictors
Ey R-people Trying to do a binary logistic regression with only categorical(age,ballot) and binary predictors for a binary response variable. I can model them at least at least i treat the binary predictors as categorical with the use of as.factor(etc) and use glm with binomial distribution and logit as link function. The problem is with interpretation of results and the use of the Wald-test to see if certain predictors are significant. When i do the wald test with standard code i see in help i can only use my whole model as input and terms 0,1 but then i take it all terms 0,1 are taken. Is there a better method for this or maybe a package or maybe an other approach? Any help would be welcomed. Frank __ 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] Multiple correlation
I'm looking for a function for the multiple correlation among three variables. I have created three vectors (x, y and z) and I want to find a correlation coefficient and evaluate its significance. Can anyone help me? Thanks in advance. [[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] output Shapiro-Wild results to a table
Hello, I have applied the Shapiro test to a matrix with 26.925 rows of data using the following F1.norm-apply(F1.n.mat,1,shapiro.test) I would now like to view and export a table of the p and W values from the Shapiro test, but I am not sure how to approach this. I have tried the following with errors. write.table(x=F1.norm,file=I:/R_Work/F1/Shapiro.csv, sep=,) Error in as.data.frame.default(x[[i]], optional = TRUE, stringsAsFactors = stringsAsFactors) : cannot coerce class 'htest' into a data.frame Any suggestions appreciated. Mary Ann F1 F1 [[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] Referencing factors through their equivalent numeric level
That did it! Thanks very much Berend. On Wed, May 2, 2012 at 4:19 AM, Berend Hasselman b...@xs4all.nl wrote: On 02-05-2012, at 07:22, Kaushik Krishnan wrote: Hey folks I'm sorry for bringing what must be a very simple question to R-help, but after some research I haven't been able to find a solution to my problem. Suppose I create a simple factor: [code] x-c(A,B,B,C,A) x [1] A B B C A x - as.factor(x) x [1] A B B C A Levels: A B C [/code] Now, when I see this factor in terms of its numeric level values, I get [code] as.numeric(x) [1] 1 2 2 3 1 [/code] Suppose I have [code] y - 2 [/code] I want the numeric value of y to reference the level of factor x. That is, I am looking for a function (`foo') so that I will get the following [code] foo(y) #or maybe foo(y,x) [1] B [/code] I can think of a roundabout way of doing through a user defined function, but I am sure that there is a built-in function that offers this functionality. I'd be grateful if someone could tell me what that function is. Maybe this? levels(x)[y] Berend -- Kaushik Krishnan (kaushik.s.krish...@gmail.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.