Re: [R] Re peated Measure ANOVA-Old question
Hi Chunhao, I google the website and I found that there are three ways to perform repeated measure ANOVA: aov, lme and lmer. It's also a good idea to search through the archives. I use the example that is provided in the above link and I try tt-aov(p.pa~group*time+Error(subject/time),data=P.PA) TukeyHSD(tt) Error in UseMethod(TukeyHSD) : no applicable method for TukeyHSD Because of ... + Error(). See the following thread, where this is answered: http://www.nabble.com/Tukey-HSD-(or-other-post-hoc-tests)-following-repeated-measures-ANOVA-td17508294.html#a17559307 HTH, Mark. ctu wrote: Hi R users, I google the website and I found that there are three ways to perform repeated measure ANOVA: aov, lme and lmer. http://www.mail-archive.com/[EMAIL PROTECTED]/msg58502.html But the questions are which one is good to use and how to do post-hoc test? I use the example that is provided in the above link and I try tt-aov(p.pa~group*time+Error(subject/time),data=P.PA) TukeyHSD(tt) Error in UseMethod(TukeyHSD) : no applicable method for TukeyHSD Any suggestions? Appreciate in advance~ Chunhao __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/Repeated-Measure-ANOVA-Old-question-tp18726146p18726722.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] Urgent
Hi Yunlei, Is your problem constrained or not? If it is unconstrained and your matrix is not positive definite, the minimum is unbounded (unless you are extremely lucky and the matrix is positive semi-definite and the vector which multiplies the unknowns is exactly perpendicular to all the eigenvectors with 0 eigenvalues). If the problem is constrained you may use regular optimization functions (like optim). Regards, Moshe. --- On Tue, 22/7/08, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: From: [EMAIL PROTECTED] [EMAIL PROTECTED] Subject: [R] Urgent To: r-help@r-project.org Received: Tuesday, 22 July, 2008, 6:12 PM Hi everyone I try to use the solve.QP to solve the quadratic programming problem. But the Dmat in the funciotn is non-positive definite. Can anyone tell me which R function can deal with the quadratic programming with non positive definite Dmat matrix ( in solve.QP) I really appreaciated. Yunlei Hu ___ This e-mail may contain information that is confidential, privileged or otherwise protected from disclosure. If you are not an intended recipient of this e-mail, do not duplicate or redistribute it by any means. Please delete it and any attachments and notify the sender that you have received it in error. Unless specifically indicated, this e-mail is not an offer to buy or sell or a solicitation to buy or sell any securities, investment products or other financial product or service, an official confirmation of any transaction, or an official statement of Barclays. Any views or opinions presented are solely those of the author and do not necessarily represent those of Barclays. This e-mail is subject to terms available at the following link: www.barcap.com/emaildisclaimer. By messaging with Barclays you consent to the foregoing. Barclays Capital is the investment banking division of Barclays Bank PLC, a company registered in England (number 1026167) with its registered offi! ce at 1 Churchill Place, London, E14 5HP. This email may relate to or be sent from other members of the Barclays Group. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Re peated Measure ANOVA-Old question
Tank you (Anna Mark) very much for this super information Let me confirm that IF I want to perform the RM-ANOVA I should use lmer and perform the post-hoc test by using glht, right? Because I am not so familiar with lmer so I have two more questions. Let me use that following example again, 1. Is the random effect statement correct? if no what will be? 2. What did I do wrong in glht? require(lme4);require(nlme) group -rep(rep(1:2, c(5,5)), 3);time -rep(1:3, rep(10,3));subject - rep(1:10,3) p.pa - c(92, 44, 49, 52, 41, 34, 32, 65, 47, 58, 94, 82, 48, 60, 47, 46, 41, 73, 60, 69, 95, 53, 44, 66, 62, 46, 53, 73, 84, 79) P.PA - data.frame(subject, group, time, p.pa) P.PA$group=factor(P.PA$group);P.PA$time=factor(P.PA$time) P.PA$subject=factor(P.PA$subject) tlmer-lmer (p.pa ~ time * group + (time*group | subject), data=P.PA ) summary(glht(tlmer,linfct=mcp(group=Tukey))) Error in UseMethod(fixef) : no applicable method for fixef In addition: Warning message Thank you very much Chunhao __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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 command history -- can it be like Matlab's?
l == losemind [EMAIL PROTECTED] on Tue, 29 Jul 2008 12:23:36 -0700 (PDT) writes: l Hi all, l In R GUI window, if you use up and down key, you will be able to recall l the previous and next command that has been used and stored in the command l history cache. l But there is one inconvenience: as Prof. Ripley said already, this is only an inconvenience for those who are used aka addicted to such behavior l In Matlab, you can type the first a few characters of the command that you l previously used, l and then press “up key, you will be able to get to that previous command l very fast, l no matter how long ago it has been used... no matter how long? ... as of ten years ago ? ;-) ;-) Anyway --- as nobody said so till now, and the vi-aficionados have already raised the flag --- I'd like to remark that the behaviour you desire has been the default behavior in ESS (The Emacs Speaks Statistics plugin for Emacs, http://ess.r-project.org/ ) for many months now. l In R GUI, there is no such functionality. l Any thoughts on making R work my productivity? leaving R GUI for ESS :-) :-) For Windows, there's a very nice package of Emacs, bundled with ESS (and AucTeX, *the* recommended LaTeX plugin for Emacs) thanks to Vincent Goulet, at http://vgoulet.act.ulaval.ca/en/ressources/emacs/ Martin Maechler, ETH Zurich l -- l Also where do I find good debugger for R? l Thanks! __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] What's the best way to operate R from within Excel?
have a look at http://sunsite.univie.ac.at/rcom/server/doc/RExcel.html regards, PF 2008/7/30 losemind [EMAIL PROTECTED]: Hi all, How do I operate R from within Excel? I mean, highlight a bunch of cells, and send to R, and do some statistics in R, and return back the numbers and do some plots in R. For example, I have some parameters for Gaussian Random variable, and I would find the most convenient way to send these numbers to R and do some plots... How to do that? Thanks a lot! -- View this message in context: http://www.nabble.com/What%27s-the-best-way-to-operate-R-from-within-Excel--tp18722737p18722737.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] problem with nested loops
Dear all, I have a problem with constructing a nested loop. I have two matrices: pnr: 800 rows 14 columns where rows are 40x20 meaning that 40 rows belong to one of twenty objects in the matrix pnr mvp: 20 rows and 14 columns I want to: calculate a distance value with the first 40 rows of pnr but 20times with the 1st row of mvp then the next 40 rows of pnr and 20times with the second row of mvp and so on. in total 20 times. i tried with: dim(p) [1] 800 14 dim(mvp) [1] 20 14 specdist -matrix(NA,nrow=40,ncol=20) for (j in 1:40){ for(i in 1:20){ specdist[j,i]-sqrt((pnr[i,1]-mvp[i,1])^2+(pnr[i,2]-mvp[i,2])^2)++(pnr[i,14]-mvp[i,14])^2)) } } but it only repeats from 1:40 and does not step from 41 to 80; from 81 to 40 etc. certainly there is a if else next step?? or while missing, but I never implemented one of those. :( I would be very grateful for any help! thank you Jens __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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
Hello, What the tilde and dot means? I believe is something to do with formula, but how do they work? An example: (fk5 ~ ., size = 10) Do you know what the fk5 ~ . means? Thank you! Renata - Email sent from www.virginmedia.com/email Virus-checked using McAfee(R) Software and scanned for spam __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Re peated Measure ANOVA-Old question
Hi Chunhao, If you carefully read the posting that was referred to you will see that lme() and not lmer() was used as an example (for using with the multcomp package). lmer() was only mentioned as an aside... lmer() is S4 and doesn't work with multcomp, which is S3. Apropos of specifying random effects: an example was given in the posting showing that aov(... +Error(...)) and lme(..., random =...) give the same result. Use that as your guideline. HTH, Mark. ctu wrote: Tank you (Anna Mark) very much for this super information Let me confirm that IF I want to perform the RM-ANOVA I should use lmer and perform the post-hoc test by using glht, right? Because I am not so familiar with lmer so I have two more questions. Let me use that following example again, 1. Is the random effect statement correct? if no what will be? 2. What did I do wrong in glht? require(lme4);require(nlme) group -rep(rep(1:2, c(5,5)), 3);time -rep(1:3, rep(10,3));subject - rep(1:10,3) p.pa - c(92, 44, 49, 52, 41, 34, 32, 65, 47, 58, 94, 82, 48, 60, 47, 46, 41, 73, 60, 69, 95, 53, 44, 66, 62, 46, 53, 73, 84, 79) P.PA - data.frame(subject, group, time, p.pa) P.PA$group=factor(P.PA$group);P.PA$time=factor(P.PA$time) P.PA$subject=factor(P.PA$subject) tlmer-lmer (p.pa ~ time * group + (time*group | subject), data=P.PA ) summary(glht(tlmer,linfct=mcp(group=Tukey))) Error in UseMethod(fixef) : no applicable method for fixef In addition: Warning message Thank you very much Chunhao __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/Repeated-Measure-ANOVA-Old-question-tp18726146p18727795.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] Coarsening the Resolution of a Dataset
Hi - thanks for the advice - I am however applying this to the whole data frame. And the code that I'm using is just to read in the data (using read.table) and then the code that you supplied. I could send you the actual dataset if you don't mind a file ~50MB?! Thanks again, Steve Date: Tue, 29 Jul 2008 15:34:31 -0400 From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] Subject: Re: [R] Coarsening the Resolution of a Dataset CC: r-help@r-project.org I assume that you are doing this on one column of the matrix which should only have 2160 entries in it. can you send the actual code you are using. I tried it with 10,000 samples and it works fine. So I need to understand the data structure you are using. Also the infinite recursion sounds strange; do you have function like 'cut' or 'c' redefined? So it would help if you could supply a reproducible example. On Tue, Jul 29, 2008 at 10:09 AM, Steve Murray [EMAIL PROTECTED] wrote: Unfortunately, when I get to the 'myCuts' line, I receive the following error: Error: evaluation nested too deeply: infinite recursion / options(expressions=)? ...and I also receive warnings about memory allocation being reached (even though I've already used memory.limit() to maximise the memory) - this is a fairly sizeable dataset afterall, 2160 rows by 4320 columns. Therefore I was wondering if there are any alternative ways of coarsening a dataset? Or are there any packages/commands built for this sort of thing? Any advice would be much appreciated! Thanks again, Steve _ Find the best and worst places on the planet http://clk.atdmt.com/UKM/go/101719807/direct/01/ -- Jim Holtman Cincinnati, OH +1 513 646 9390 What is the problem you are trying to solve? _ 100s of Nikon cameras to be won with Live Search [[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] Coarsening the Resolution of a Dataset
Hi - thanks for the advice - I am however applying this to the whole data frame. And the code that I'm using is just to read in the data (using read.table) and then the code that you supplied. I could send you the actual dataset if you don't mind a file ~50MB?! Thanks again, Steve Date: Tue, 29 Jul 2008 15:34:31 -0400 From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] Subject: Re: [R] Coarsening the Resolution of a Dataset CC: r-help@r-project.org I assume that you are doing this on one column of the matrix which should only have 2160 entries in it. can you send the actual code you are using. I tried it with 10,000 samples and it works fine. So I need to understand the data structure you are using. Also the infinite recursion sounds strange; do you have function like 'cut' or 'c' redefined? So it would help if you could supply a reproducible example. On Tue, Jul 29, 2008 at 10:09 AM, Steve Murray wrote: Unfortunately, when I get to the 'myCuts' line, I receive the following error: Error: evaluation nested too deeply: infinite recursion / options(expressions=)? ...and I also receive warnings about memory allocation being reached (even though I've already used memory.limit() to maximise the memory) - this is a fairly sizeable dataset afterall, 2160 rows by 4320 columns. Therefore I was wondering if there are any alternative ways of coarsening a dataset? Or are there any packages/commands built for this sort of thing? Any advice would be much appreciated! Thanks again, Steve _ Find the best and worst places on the planet http://clk.atdmt.com/UKM/go/101719807/direct/01/ -- Jim Holtman Cincinnati, OH +1 513 646 9390 What is the problem you are trying to solve? _ Play and win great prizes with Live Search and Kung Fu Panda __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Eclipse/Statet: How to set breakpoints
Hi, I'm using the IDE Eclipse with the Statet-Plugin to develop R-code. Is there a possibility to set breakpoints for debugging in R-script files (just like in Java-code)? Cheers, Eli __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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 command history -- can it be like Matlab's?
Prof Brian Ripley wrote: A patch to do this was posted on 2007-09-29 by Glenn Davis. Some people not addicted to Matlab find the behaviour very inconvenient and prefer the getline/readline behaviour (triggered by ^R/^S) of Rterm and R on Unixen. Now that you've mentioned readline, it doesn't behave exactly the same in Bash and R: if you press ctrl-r and then ctrl-c in Bash, it breaks the search and you go back to the prompt as normal. In R on Linux (all versions I've tried, 2.2 to 2.7.1), doing that returns you to the prompt but you can't type anything, and the input buffer retains the text from the search, so pressing enter makes the historical command run again. Try this: ls() character(0) [ctrl-r] (reverse-i-search)`l': ls() [ctrl-c, then enter] ls() character(0) -- Gad Abraham Dept. CSSE and NICTA The University of Melbourne Parkville 3010, Victoria, Australia email: [EMAIL PROTECTED] web: http://www.csse.unimelb.edu.au/~gabraham __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] need some help
Hi Can any body explain the meaning of the following R code if(interactive()) stop(msg, call. = FALSE) else quit() Thanks K.Ravichandra [[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] Howto Draw Bimodal Gamma Curve with User Supplied Parameters
can you write the bimodal gamma pdf? if so create your own pdf: dbigamma=function(x,alpha1,alpha2,beta1,beta2) { # ... the bimodal gamma pdf (I can't find it) } hist(x,probability=T) curve(dbigamma(x,alpha1,alpha2,beta1,beta2)) and look at the result regards, PF 2008/7/29 Gundala Viswanath [EMAIL PROTECTED]: Hi, Suppose I have the following vector (data points): x [1] 36.0 57.3 73.3 92.0 300.4 80.9 19.8 31.4 85.8 44.9 24.6 48.0 [13] 28.0 38.3 85.2 103.6 154.4 128.5 38.3 72.4 122.7 123.1 41.8 21.7 [25] 143.6 120.2 46.6 29.2 44.8 25.0 57.3 96.4 29.4 62.9 66.4 30.0 [37] 24.1 14.8 56.6 102.4 117.5 90.4 37.2 79.6 27.8 17.1 26.6 16.3 [49] 41.4 48.9 24.1 23.3 9.9 11.5 15.0 23.6 29.3 27.0 19.2 18.7 [61] 4.1 13.0 3.3 5.5 38.2 8.5 39.6 39.2 16.1 35.3 23.3 31.5 [73] 38.8 51.5 28.4 18.8 24.1 25.4 28.8 32.8 31.0 28.8 33.3 55.5 [85] 39.2 21.0 43.7 16.3 50.6 34.6 66.3 50.5 59.4 46.7 51.9 125.6 [97] 69.8 43.7 86.8 50.6 132.4 56.0 6.1 4.9 7.1 7.1 12.8 12.1 [109] 164.2 69.3 15.6 11.4 34.3 9.2 17.6 21.7 19.2 30.7 61.1 35.8 [121] 185.8 118.4 13.0 9.6 19.1 45.2 94.5 248.0 56.3 24.4 13.8 12.8 [133] 35.0 31.6 22.5 50.1 18.7 22.1 28.3 39.5 48.2 33.1 43.5 35.1 [145] 37.4 30.3 15.8 13.9 15.3 16.1 12.7 11.4 13.0 13.8 31.5 25.3 [157] 65.2 39.5 And the following parameter set (2 component) for gamma function. comp.1comp.2 alpha (shape) 2.855444 2.152056 beta (scale) 10.418785 39.296224 These params are predefined/precalculated by user. My question is how can I create a bimodal gamma curve - based on the two parameter set - on top of the histogram of data points above? - Gundala Viswanath Jakarta - Indonesia __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Need help
Hello, Can someone help me to understand the meaning of the following R line? list(fk5 ~ .) Thanks, Renata - Email sent from www.virginmedia.com/email Virus-checked using McAfee(R) Software and scanned for spam __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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 command history -- can it be like Matlab's?
Here is the post where Prof Ripley is reffering to: http://tolstoy.newcastle.edu.au/R/e2/help/07/09/26668.html Bart losemind wrote: Prof Brian Ripley wrote: A patch to do this was posted on 2007-09-29 by Glenn Davis. Some people not addicted to Matlab find the behaviour very inconvenient and prefer the getline/readline behaviour (triggered by ^R/^S) of Rterm and R on Unixen. On Tue, 29 Jul 2008, losemind wrote: Hi all, In R GUI window, if you use up and down key, you will be able to recall the previous and next command that has been used and stored in the command history cache. But there is one inconvenience: Or an inconvenience of Matlab not shared by R, depending on your preferences. In Matlab, you can type the first a few characters of the command that you previously used, and then press “up key, you will be able to get to that previous command very fast, no matter how long ago it has been used... In R GUI, there is no such functionality. Any thoughts on making R work my productivity? -- Also where do I find good debugger for R? Thanks! -- View this message in context: http://www.nabble.com/R-command-historycan-it-be-like-Matlab%27s--tp18719530p18719530.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. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Hi, I don't find Glenn Davis's patch... where is it? I like that Matlab feature. And I am using R GUI on windows... Please help me! Please also give me pointers to good R debuggers? Thanks! -- View this message in context: http://www.nabble.com/R-command-historycan-it-be-like-Matlab%27s--tp18719530p18728916.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] Need help
Can someone help me to understand the meaning of the following R line? list(fk5 ~ .) fk5 ~. is a formula, most likely used by a regression (or similar model). fk5 is the response variable, and the dot is a placeholder for 'whatever was on that side of the formula before'. (This is usually used for updating models.) list() places the formula in a list, obviously. It's hard to provide more meaning without the context. (Also, mailing list etiquette suggests you should provide a more informative subject line than 'need help'.) Regards, Richie. Mathematical Sciences Unit HSL ATTENTION: This message contains privileged and confidential inform...{{dropped:20}} __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Re peated Measure ANOVA-Old question
On Wed, 2008-07-30 at 00:49 -0700, Mark Difford wrote: Hi Chunhao, If you carefully read the posting that was referred to you will see that lme() and not lmer() was used as an example (for using with the multcomp package). lmer() was only mentioned as an aside... lmer() is S4 and doesn't work with multcomp, which is S3. That is not true (but it may once have been?). multcomp ``suggests'' lme4 and is distributed with a vignette that has a lmer example with the same random effect expression as the R-Help thread you directed the OP to read. The OP's example works for me with latest CRAN versions of multcomp, lme4 and Matrix installed (well, with a warning about false convergence from nlminb in the lmer call and a warning from the call to glht about the covariate interaction and questioning if the default contrasts are appropriate - all things for Chunhao to consider himself me thinks...). Chunhoa, I'm not familiar enough with lme4 to know what is the correct way to specify the random effects you want. You could consider moving this onto the R-mixed-models SIG: https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models or search the archives of that list as lmer/lm4 are discussed there quite a lot. HTH G Apropos of specifying random effects: an example was given in the posting showing that aov(... +Error(...)) and lme(..., random =...) give the same result. Use that as your guideline. HTH, Mark. ctu wrote: Tank you (Anna Mark) very much for this super information Let me confirm that IF I want to perform the RM-ANOVA I should use lmer and perform the post-hoc test by using glht, right? Because I am not so familiar with lmer so I have two more questions. Let me use that following example again, 1. Is the random effect statement correct? if no what will be? 2. What did I do wrong in glht? require(lme4);require(nlme) group -rep(rep(1:2, c(5,5)), 3);time -rep(1:3, rep(10,3));subject - rep(1:10,3) p.pa - c(92, 44, 49, 52, 41, 34, 32, 65, 47, 58, 94, 82, 48, 60, 47, 46, 41, 73, 60, 69, 95, 53, 44, 66, 62, 46, 53, 73, 84, 79) P.PA - data.frame(subject, group, time, p.pa) P.PA$group=factor(P.PA$group);P.PA$time=factor(P.PA$time) P.PA$subject=factor(P.PA$subject) tlmer-lmer (p.pa ~ time * group + (time*group | subject), data=P.PA ) summary(glht(tlmer,linfct=mcp(group=Tukey))) Error in UseMethod(fixef) : no applicable method for fixef In addition: Warning message Thank you very much Chunhao __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Coarsening the Resolution of a Dataset
Can you at least send the output from the script so that we can see exactly how you are reading in the data and then processing it. Doing 'str(yourData)' would help to understand what the data looks like. The exactly error messages would also help. Is the data entirely numeric, or does it also contain factors? So this type of information is needed to understand the context of where your problem is. On Wed, Jul 30, 2008 at 4:09 AM, Steve Murray [EMAIL PROTECTED] wrote: Hi - thanks for the advice - I am however applying this to the whole data frame. And the code that I'm using is just to read in the data (using read.table) and then the code that you supplied. I could send you the actual dataset if you don't mind a file ~50MB?! Thanks again, Steve Date: Tue, 29 Jul 2008 15:34:31 -0400 From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] Subject: Re: [R] Coarsening the Resolution of a Dataset CC: r-help@r-project.org I assume that you are doing this on one column of the matrix which should only have 2160 entries in it. can you send the actual code you are using. I tried it with 10,000 samples and it works fine. So I need to understand the data structure you are using. Also the infinite recursion sounds strange; do you have function like 'cut' or 'c' redefined? So it would help if you could supply a reproducible example. On Tue, Jul 29, 2008 at 10:09 AM, Steve Murray wrote: Unfortunately, when I get to the 'myCuts' line, I receive the following error: Error: evaluation nested too deeply: infinite recursion / options(expressions=)? ...and I also receive warnings about memory allocation being reached (even though I've already used memory.limit() to maximise the memory) - this is a fairly sizeable dataset afterall, 2160 rows by 4320 columns. Therefore I was wondering if there are any alternative ways of coarsening a dataset? Or are there any packages/commands built for this sort of thing? Any advice would be much appreciated! Thanks again, Steve _ Find the best and worst places on the planet http://clk.atdmt.com/UKM/go/101719807/direct/01/ -- Jim Holtman Cincinnati, OH +1 513 646 9390 What is the problem you are trying to solve? _ Play and win great prizes with Live Search and Kung Fu Panda http://clk.atdmt.com/UKM/go/101719966/direct/01/ -- Jim Holtman Cincinnati, OH +1 513 646 9390 What is the problem you are trying to solve? __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] need some help
I assume that it is testing to see if you are in the interactive mode (typically using RGUI or Rterm) and not a batch file. If it is interactive, it issues a 'stop' (this lets the person take action on the problem). If in the batch, it just terminates the execution of the script. On Wed, Jul 30, 2008 at 4:44 AM, Kurapati, Ravichandra (Ravichandra) [EMAIL PROTECTED] wrote: Hi Can any body explain the meaning of the following R code if(interactive()) stop(msg, call. = FALSE) else quit() Thanks K.Ravichandra [[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. -- Jim Holtman Cincinnati, OH +1 513 646 9390 What is the problem you are trying to solve? __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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 nested loops
What you need is chapter 9 in http://cran.r-project.org/doc/manuals/R-intro.pdf . And you could also use chapter 2, especially 2.2. specdist -matrix(NA,nrow=40,ncol=20) for (j in 1:40){ for(i in 1:20){ specdist[j,i]-sqrt((pnr[i,1]-mvp[i,1])^2+(pnr[i,2]-mvp[i,2])^2)++(pnr[i,14]-mvp[i,14])^2)) } } but it only repeats from 1:40 and does not step from 41 to 80; from 81 to 40 etc. certainly there is a if else next step?? or while missing, but I never implemented one of those. :( It does exactly what you've told it to do. And if(you really insist on using loops) it would be easy to add another loop that would go from 0 to 40 to 80 etc: for(another.unnecessary.loop in seq(0,800,40){ # and now add that one to i for pnr And things like dist() might make calculating distance matrices /see: help(dist) / a bit easier. As you see from documentation, it calculates distances between rows of a matrix; so you can first rbind your 2 matrices, then use dist, and then extract the part you want. Or at least you might want to consider making your calculations simpler by using vectors in a decent way: sqrt(sum((pnr[i,]-mvp[i,])^2 )) # instead of adding them one by one good luck, Kenn On Wed, Jul 30, 2008 at 10:49 AM, Jens Oldeland [EMAIL PROTECTED] wrote: Dear all, I have a problem with constructing a nested loop. I have two matrices: pnr: 800 rows 14 columns where rows are 40x20 meaning that 40 rows belong to one of twenty objects in the matrix pnr mvp: 20 rows and 14 columns I want to: calculate a distance value with the first 40 rows of pnr but 20times with the 1st row of mvp then the next 40 rows of pnr and 20times with the second row of mvp and so on. in total 20 times. i tried with: dim(p) [1] 800 14 dim(mvp) [1] 20 14 specdist -matrix(NA,nrow=40,ncol=20) for (j in 1:40){ for(i in 1:20){ specdist[j,i]-sqrt((pnr[i,1]-mvp[i,1])^2+(pnr[i,2]-mvp[i,2])^2)++(pnr[i,14]-mvp[i,14])^2)) } } but it only repeats from 1:40 and does not step from 41 to 80; from 81 to 40 etc. certainly there is a if else next step?? or while missing, but I never implemented one of those. :( I would be very grateful for any help! thank you Jens __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] read XML
I have a xml exported by Manifold GIS but I'm not being able to import it into R using XLM package. The file have this structure: ?xml version=1.0 encoding=UTF-8 ? - layout nameLayout 2/name pagesByX1/pagesByX pagesByY1/pagesByY - elements legend refParent=r3 xmax=0.54156171284634758 xmin=0.020151133501259435 ymax=0.31480598161051165 ymin=0.042461931948864044 / component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8 borderFore=#00 borderMargin=12 borderNoOverlaps=true borderRounding=0 borderStep=1 borderUnit=Meter controlPoints=auto graticule=auto grid=auto legend=auto name=MapMnaziBayhab northArrow=auto paging=continuous ref=r1 scaleBar=auto scope=locked center / scale scopeDetail=646802.61034615175,8856311.5759953968,150 xmax=0.35877862595419846 xmin=0.027989821882951665 ymax=0.98902384414662947 ymin=0.32371064328183174 / component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8 borderFore=#00 borderMargin=12 borderNoOverlaps=true borderRounding=0 borderStep=1 borderUnit=Meter controlPoints=auto graticule=auto grid=auto legend=hide name=MapMnaziBayall northArrow=auto paging=continuous ref=r3 scaleBar=auto scope=locked center / scale scopeDetail=646802.61034615175,8856311.5759953968,150 xmax=0.707379134860051 xmin=0.37659033078880411 ymax=0.98902384414662947 ymin=0.32371064328183174 / component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8 borderFore=#00 borderMargin=12 borderNoOverlaps=true borderRounding=0 borderStep=1 borderUnit=Degree controlPoints=auto graticule=auto grid=auto legend=auto name=Map Africa Mnazi northArrow=auto paging=continuous ref=r6 scaleBar=auto scope=entire component xmax=0.93198992443324935 xmin=0.73047858942065491 ymax=0.98902384414662947 ymin=0.84662172667648694 / /elements /layout Any idea? Thanks. Paulo Cardoso [[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] function to transform response of a formula
Hi, I am trying to write a function which takes a formula as input and outputs a new formula with a different response while keeping the rest of the formula the same. I.e. respapply : ( y ~ a+b ) - ( f(y) ~ a + b ) I have tried the following but it doesn't work. The terms become invalid as shown below. respapply - function(fm, f) { fm[[2]] - f(eval(fm[[2]])) fm; } fm - formula(y ~ a + b) y - runif(5) newfm - respapply(fm,identity) newfm c(0.552921097259969, 0.939932722365484, 0.62522904924117, 0.899310540175065, 0.877736972644925) ~ a + b terms(newfm) Error in terms.formula(fmapply(fm, identity)) : invalid term in model formula Could someone put me in the right direction of how to correctly write a respapply function as described. Regards, Paul Emberson __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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 read.table()
I am sorry I just found the stupid mistake. I did not specify dec=, because I usually use . Anyway thanks for having the opportunity to get help in this list. B. Birgitle wrote: Hello R-User I have a table as tab-delimited textfile (291 rows, 83 columns). The first row are labels and the first line the variable names. I used the following code several times with different similar tables and it always worked. But now: setClass(of) setAs(character, of, function(from) as.ordered(from)) Classe82-cclasses - c(rep(factor, 63), rep(numeric,7), rep (of, 12)) Table-read.table(Table.txt,header=TRUE,row.names=1, na.strings=NA ,colClasses = Classe82) I get this error-message: Fehler in scan(file, what, nmax, sep, dec, quote, skip, nlines, na.strings, : scan() erwartete 'a real', bekam '8,5' Error in scan(file, what, nmax, sep, dec, quote, skip, nlines, na.strings, : scan() expected 'a real', got '8,5' It seems that the error is in the colClasses-argument. Without this argument it reads the table. I checked allready if there are empty cells or blanks in the header but could not find. Maybe that its just a simple thing and I know that I can change the classes after reading in the table, but I really would like to know how to do this right. I would be very glad if somebody has an idea, or could tell me, how I could find out, what`s going wrong. Many thanks in advance B. - The art of living is more like wrestling than dancing. (Marcus Aurelius) -- View this message in context: http://www.nabble.com/problem-with-read.table%28%29-tp18729348p18729917.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] problem with read.table()
Table-read.table(Table.txt,header=TRUE,row.names=1, na.strings=NA ,colClasses = Classe82) Fehler in scan(file, what, nmax, sep, dec, quote, skip, nlines, na.strings, : scan() erwartete 'a real', bekam '8,5' Error in scan(file, what, nmax, sep, dec, quote, skip, nlines, na.strings, : scan() expected 'a real', got '8,5' It looks like your tab separated file uses ',' as a decimal point (german convention) while read.table expects '.'. Try giving the dec=, option to read.table. cu Philipp -- Dr. Philipp Pagel Lehrstuhl für Genomorientierte Bioinformatik Technische Universität München Wissenschaftszentrum Weihenstephan 85350 Freising, Germany http://mips.gsf.de/staff/pagel __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Bizarre - R crashes on merge
Hi all, I have a large data.frame, 1530 observation with 6 columns. I want to merge a 7th column, a transformation of the response variable (hospital admissions), namely trans-sqrt(copd$admissions+0.25) trans-data.frame(trans) And now when I do copd2-merge(copd,trans) (copd being my original data.frame), R either crashes or is taking an extremely long time to do the computation. I had expected the computation to be done almost instantly as I have done similar things in R recently, however my system becomes very slow to the point of being unusable. Would people expect this computation to take a long time? Most of the data in the data.frame are just integers. I want to perform linear regression on the data trans, so I would like it in the data.frame to save typing. Any ideas? Robin Williams Met Office summer intern - Health Forecasting [EMAIL PROTECTED] [[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] Need help
See ?formula ?terms.formula or ask the author of the line (it doesn't make much sense to use '.' unless you have a 'data' argument to pass to terms()). On Wed, 30 Jul 2008, [EMAIL PROTECTED] wrote: Hello, Can someone help me to understand the meaning of the following R line? list(fk5 ~ .) Thanks, Renata - Email sent from www.virginmedia.com/email Virus-checked using McAfee(R) Software and scanned for spam __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Need help
On Wed, 30 Jul 2008, [EMAIL PROTECTED] wrote: Can someone help me to understand the meaning of the following R line? list(fk5 ~ .) fk5 ~. is a formula, most likely used by a regression (or similar model). fk5 is the response variable, and the dot is a placeholder for 'whatever was on that side of the formula before'. (This is usually used for updating models.) That's the meaning only for update.formula() AFAIK: the far more common meaning is given in ?terms.formula. list() places the formula in a list, obviously. It's hard to provide more meaning without the context. (Also, mailing list etiquette suggests you should provide a more informative subject line than 'need help'.) Regards, Richie. Mathematical Sciences Unit HSL -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Eclipse/Statet: How to set breakpoints
On 30/07/2008 4:28 AM, [EMAIL PROTECTED] wrote: Hi, I'm using the IDE Eclipse with the Statet-Plugin to develop R-code. Is there a possibility to set breakpoints for debugging in R-script files (just like in Java-code)? I believe the answer is no, but R does contain (some of?) the necessary infrastructure to add that. It will just take some time, and some happy coincidences. (I don't know StatET, so I'll need to learn what it needs.) 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] Bizarre - R crashes on merge
I have a large data.frame, 1530 observation with 6 columns. I want to merge a 7th column, a transformation of the response variable (hospital admissions), namely trans-sqrt(copd$admissions+0.25) trans-data.frame(trans) And now when I do copd2-merge(copd,trans) (copd being my original data.frame), R either crashes or is taking an extremely long time to do the computation. I had expected the computation to be done almost instantly as I have done similar things in R recently, however my system becomes very slow to the point of being unusable. If I understand correctly, all you want to do is add another column to your data.frame. Unless I have overlooked something, a simple assignement should do: copd$trans - copd$admissions+0.25 The reason your computation takes long/crashes is that you are merging two data frames which have no common columns to merge on. So merge() is generating all possible combinations for you. a = data.frame(1:3) b = data.frame(4:6) merge(a,b) X1.3 X4.6 114 224 334 415 525 635 716 826 936 This is most likely not what you intended. I guess you were looking for cbind() rather than merge() cu Philipp -- Dr. Philipp Pagel Lehrstuhl für Genomorientierte Bioinformatik Technische Universität München Wissenschaftszentrum Weihenstephan 85350 Freising, Germany http://mips.gsf.de/staff/pagel __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] table questions
On Tue, 2008-07-29 at 11:28 -0500, Edna Bell wrote: Hi again! Suppose I have the following: xy - round(rexp(20),1) xy [1] 0.1 3.4 1.6 0.4 1.0 1.4 0.2 0.3 1.6 0.2 0.0 0.1 0.1 1.0 2.0 0.9 2.5 0.1 1.5 0.4 table(xy) xy 0 0.1 0.2 0.3 0.4 0.9 1 1.4 1.5 1.6 2 2.5 3.4 1 4 2 1 2 1 2 1 1 2 1 1 1 Is there a way to set things up to have 0 - 0.4 0.5 - 0.9 etc. please? I know there is the cut functions, but breaks are required. If you don't have breaks, what should you do, please? Would using the breaks from the hist function work appropriately, please? Well, Edna, this looked like fun, so here is something that may help you out. lumpyTable-function(x,breaks) { xcounts-hist(x,breaks=breaks,plot=FALSE)$counts nbreaks-length(breaks) binnames-paste(breaks[1:(nbreaks-1)], breaks[2:nbreaks],sep=-,collapse=\t) cat(binnames,\n,paste(xcounts,collapse=\t),\n) } xy-round(rexp(20),1) lumpyTable(xy,c(0,0.5,1,2,4)) 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] glm error: factor levels
Hello R-Users, again me! I have a data.frame with 291 rows, 82 columns. Tha variables in the columns are factors, numerics and ordered factors. The response variable is a factor with two levels. I would like to find the best model by trying every possible variable combination using a logistic regression and comparing the AIC (still have to find out how to do this fast and easy). I am aware of the step function but would like to do it also without step. But unfortunatley I have allready a problem with the first model using all variables: df.glm-glm(RespVar~.,family=binomial,data=df) I get back this: Fehler in `contrasts-`(`*tmp*`, value = contr.treatment) : Kontraste können nur auf Faktoren mit 2 oder mehr Stufen angewendet werden Error in `contrasts-`(`*tmp*`, value = contr.treatment) : contrasts can only be used for factors with two or more levels There are no variables with less than two levels in my data.frame but here are missing values (NA). I could imagine that some observations are deleted due to missingness and perhaps after that, some of the variables contain only one level. I would be happy if somebody could tell me if my speculation could be true and perhaps also how I could find out which variables I have to delete to avoid this problem. Many thanks in advance. B. - The art of living is more like wrestling than dancing. (Marcus Aurelius) -- View this message in context: http://www.nabble.com/glm-error%3A-factor-levels-tp18730487p18730487.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] function to transform response of a formula
Its ok. I've just read about update.formula in another message. Paul Paul Emberson wrote: Hi, I am trying to write a function which takes a formula as input and outputs a new formula with a different response while keeping the rest of the formula the same. I.e. respapply : ( y ~ a+b ) - ( f(y) ~ a + b ) I have tried the following but it doesn't work. The terms become invalid as shown below. respapply - function(fm, f) { fm[[2]] - f(eval(fm[[2]])) fm; } fm - formula(y ~ a + b) y - runif(5) newfm - respapply(fm,identity) newfm c(0.552921097259969, 0.939932722365484, 0.62522904924117, 0.899310540175065, 0.877736972644925) ~ a + b terms(newfm) Error in terms.formula(fmapply(fm, identity)) : invalid term in model formula Could someone put me in the right direction of how to correctly write a respapply function as described. Regards, Paul Emberson __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Bizarre - R crashes on merge
On Wed, Jul 30, 2008 at 12:24:22PM +0200, Philipp Pagel wrote: If I understand correctly, all you want to do is add another column to your data.frame. Unless I have overlooked something, a simple assignement should do: copd$trans - copd$admissions+0.25 Sorry, that should have been: copd$trans - sqrt(copd$admissions+0.25) cu Philipp -- Dr. Philipp Pagel Lehrstuhl für Genomorientierte Bioinformatik Technische Universität München Wissenschaftszentrum Weihenstephan 85350 Freising, Germany http://mips.gsf.de/staff/pagel __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] png() does not generate a 24 bit PNG file
Hi there, When I am using the png() function as the following to generate a png file on Mac OSX Tiger, I found that the bit depth is 32. But I want a 24 bit depth png. What should I do? png(filename=/Users/usg/Desktop/new.png) plot(1:20) dev.off() To avoid using cairo, and R-2.7.0 does not find a Xlib on my Mac, I also tried this one: png(filename=/Users/usg/Desktop/new.png, type =quartz ) plot(1:20) dev.off() It does not work, either. The manual says png will use a palette if there are less than 256 colours on the page, and record a 24-bit RGB file otherwise (or a 32-bit RGBA file if type = cairo and non-opaque colours are used). I don't want to set palette less than 256 colours, I just want a 24-bit png file. Could anyone help me? Thanks in advance. Long __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] FFT - (STATS) - is this correct?
Hello, I have calculated the fourier transform of the series enclosed at the end of this message, by doing: library(stats) x - readLines(file1.txt) x.num - as.numeric(x) ft.x.num - fft(x.num) My question is: why is the first value (Real) of ft.x.num that big? (954.833870) all the other values are much smaller. Am I doing something wrong? Could you please help me to understand that? Many thanks, Renata 2.24791 6.39824 7.43533 7.21367 11.2164 7.29183 9.72807 12.8445 12.4819 8.18952 6.38345 9.98463 6.25724 7.97327 8.9676 8.27709 14.8272 13.4908 11.876 11.4889 11.3161 9.79778 8.09873 4.43935 5.30657 9.37819 0 8.09507 10.9567 10.5478 12.6661 13.8612 14.025 13.9403 11.5847 9.50861 7.81196 5.4 5.27313 4.16159 3.83932 8.95892 11.9548 12.7598 11.6816 13.3388 13.1956 9.50887 12.4671 11.2608 12.6553 5.63253 4.18556 4.47097 9.13142 5.29101 11.3582 7.5489 13.0371 9.26487 11.6458 6.26179 10.4051 11.7282 9.36171 10.7723 4.90151 4.25747 6.95437 6.17832 11.59 13.894 10.8935 8.19078 6.27219 6.74875 10.076 6.47078 11.1408 6.48286 10.4232 9.23548 11.199 7.97828 13.1261 12.1624 7.90476 11.7495 14.0312 9.97212 11.3685 12.6093 4.68484 4.72131 5.10963 8.1693 8.21239 10.6743 5.39084 11.1944 12.4415 8.0419 5.62567 12.2756 0 - Email sent from www.virginmedia.com/email Virus-checked using McAfee(R) Software and scanned for spam __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] placing a text in the corner of a plot
On Wed, 2008-07-30 at 00:04 +0200, Jörg Groß wrote: Is there an easy way to add a text into an R-plot and place it in the upper left corner? Like that: | (a) | | | | | | | | | | | The (a) should be at the borders of a box defined by the box()-command. Hi Jorg, Maybe the corner.label function in plotrix will do what you want. 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] Eclipse/Statet: How to set breakpoints
On 7/30/2008 7:15 AM, [EMAIL PROTECTED] wrote: Hi Duncan, thank you for your fast answering. Is there any function implemented in R to stop it? (something like q() but i only want to stop a script not shutdown the whole R-console at a certain point) That would be a good alternative for breakpoints in Eclipse... A call to browser() will pause execution, let you examine and change local variables, etc. A few years ago I put together a web page of debugging tips; it's still online at www.stats.uwo.ca/faculty/murdoch/software/debuggingR. I think most of the information is still current, though I haven't reviewed it in a while. Duncan Murdoch Best, Eli Duncan Murdoch schrieb: On 30/07/2008 4:28 AM, [EMAIL PROTECTED] wrote: Hi, I'm using the IDE Eclipse with the Statet-Plugin to develop R-code. Is there a possibility to set breakpoints for debugging in R-script files (just like in Java-code)? I believe the answer is no, but R does contain (some of?) the necessary infrastructure to add that. It will just take some time, and some happy coincidences. (I don't know StatET, so I'll need to learn what it needs.) 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] dens function
Hi R, Is there a function called dens in R? Is it similar to density? I found this function in an RExcel demo... Or is it in a specific other package? The function is used as (=rapply(dens,A11:A1010,100,D8,-5,5)) Thanks, Shubha This e-mail may contain confidential and/or privileged i...{{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.
[R] Connecting R to PostgreSQL on Windows.
Hi All, It took me 30minutes to connect GNU R on Windows XP to a PostgreSQL database running on the same machine and then generate the first graphics. I've taken screenshots of all the steps and documented them here: http://code.google.com/p/jwanalytics/wiki/GnuRe Thanks for making it easy to do it. The help files within GNU R are excellent quality. Best regards, André Andre Cesta, Eng, MSc, SCJP, SCJA http://geocities.com/aacesta __ Not happy with your email address?. Get the one you really want - millions of new email addresses avail __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Mixed effects model where nested factor is not the repeated across treatments lme???
Hi, I have searched the archives and can't quite confirm the answer to this. I appreciate your time... I have 4 treatments (fixed) and I would like to know if there is a significant difference in metal volume (metal) between the treatments. The experiment has 5 blocks (random) in each treatment and no block is repeated across treatments. Within each plot there are varying numbers of replicates (random) (some plots have 4 individuals in them some have 14 and a range in between). NOTE the plots in one treatment are not replicated in the others. So I end up with a data.frame with 4 treatments repeated down one column (treatment=A, B, C, D), 20 plots repeated down the next (block= 1 to 20) and records for metal volume (metal- 124 of these) I have made treatment and block a factor. But haven't grouped them (do I need to and how if so) The main question is in 3 parts: 1. is this the correct formula to use for this situation: lme1-lme(metal~treatment,data=data,random=~1|block) (or is lme even the right thing to use here?) I get: summary(lme1) Linear mixed-effects model fit by REML Data: data AIC BIClogLik 365.8327 382.5576 -176.9163 Random effects: Formula: ~1 | block (Intercept) Residual StdDev: 0.4306096 0.9450976 Fixed effects: Cu ~ Treatment Value Std.Error DF t-value p-value (Intercept) 5.587839 0.2632831 104 21.223688 0. *** TreatmentB -0.970384 0.3729675 16 -2.601792 0.0193 *** TreatmentC -1.449250 0.3656351 16 -3.963651 0.0011 *** TreatmentD -1.319564 0.3633837 16 -3.631323 0.0022 *** Correlation: (Intr) TrtmAN TrtmCH TreatmentB -0.706 TreatmentC -0.720 0.508 TreatmentD -0.725 0.511 0.522 Standardized Within-Group Residuals: Min Q1 Med Q3 Max -2.85762206 -0.68568460 -0.09004478 0.56237152 3.20650288 Number of Observations: 124 Number of Groups: 20 2. if so how can I get p values for comparisons between every group... ie is A different from B, is A different from C, is A different from D, is B different from C, is B different from D etc... is there a way to get all of these instead of just is A different from B, is A different from C, is A different from D which summary seems to give? 3. last of all what is the best way to print out all the residuals for lme... I can get qqplot(lme1) is there a pre-programmed call for multiple diagnostic plots like in some other functions... Thankyou so Much for your time It is much appreciated ;-) Miki [[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] Successfully connected GNU R to PostgreSQL on windows XP.
Hi All, I guess it is also important to write when you did not have any problems doing something. This morning it took me 30minutes to connect GNU R on Windows XP to a PostgreSQL database running on the same machine and then generate the first graphics. I've taken screenshots of all the steps and documented them here: http://code.google.com/p/jwanalytics/wiki/GnuRe Thanks for making it easy to do it. The help files within GNU R are excellent quality. Best regards, André Andre Cesta, Eng, MSc, SCJP, SCJA http://geocities.com/aacesta __ Not happy with your email address?. Get the one you really want - millions of new email addresses avail __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] R GUI help
Hi R gurus Im currently doing some GUI coding with the rpanel package. I have come across a very interesting problem, how do I close a panel that I have created. This sounds silly for I can always click the X up in the right corner but how do I do it by code? for example; when I create a control I know the objects name. test = rp.control() and test will have this format '.rpanel', but can I call the control ID and close the object? Regards Tom -- View this message in context: http://www.nabble.com/R-GUI-help-tp18729462p18729462.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] adding lines to multiple plots
Hi I am trying to add density lines to multiple histograms created using R. I have managed to get all 18 lines on the last histogram in the series, however, i cannot figure out how to get each line appear on the correct histogram plot. I know in Matlab there is a hold function, is there something similar in R? the following is the code i have used to get mutiple plots and then add all the lines to the final plot: ##find unique column names in table variablenames-unique(names(variables)) ## define number of unique names Nvariables-length(variablenames) ##for loop required for labelling of histograms and to tell how many hist to make for(i in 1:Nvariables){ par(mfrow=c(1,1),ask=TRUE) } ##use lapply for dataframes creates hist for each variable and labels corresponding ##important to have this outside of loop lapply(names(variables),function(i)hist(variables[[i]],probability=T,main=paste(Histogram of,i), xlab=paste(i))) for(i in 1:Nvariables){ lines(density(variables[[i]],lwd=2)) } I am pretty sure its a simple explanation, i have just run out of ideas. Thanks gary Watmough PhD Student University of Southamton School of Geography -- View this message in context: http://www.nabble.com/adding-lines-to-multiple-plots-tp18730581p18730581.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] Re creating Procrustes Plot in Lattice
Hi, I have been trying to create a function to generate a Procrustes plot, generated from package vegan in lattice. standard vegan code as follows library(vegan) pro=protest(P1, P8, permutations=4999,choices=1:4) plot(pro) Now, here is the code for the function that I have failed to get to work properly. panel.procrustes=function(x,y) }Pro=protest(x,y,permutations=4999,choices=1:4) Proplot=plot(Pro) } xyplot(P1[1:4]~P8[1:4],panel=panel.procrustes) I can generate an empty plot, but not much else - hope someone can help and point out the obvious! Kind regards Andrew http://www.nabble.com/file/p18731653/P1.csv P1.csv http://www.nabble.com/file/p18731653/P8.csv P8.csv -- View this message in context: http://www.nabble.com/Recreating-Procrustes-Plot-in-Lattice-tp18731653p18731653.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] read XML
Paulo Cardoso [EMAIL PROTECTED] writes: I have a xml exported by Manifold GIS but I'm not being able to import it into R using XLM package. I can library(XML) xml - xmlTreeParse(tmp.xml, useInternal=TRUE) xpathApply(xml, //component/@ymin, xmlValue) [[1]] [1] 0.32371064328183174 [[2]] [1] 0.32371064328183174 [[3]] [1] 0.84662172667648694 so I wonder what specifically your difficulty is? Best, Martin The file have this structure: ?xml version=1.0 encoding=UTF-8 ? - layout nameLayout 2/name pagesByX1/pagesByX pagesByY1/pagesByY - elements legend refParent=r3 xmax=0.54156171284634758 xmin=0.020151133501259435 ymax=0.31480598161051165 ymin=0.042461931948864044 / component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8 borderFore=#00 borderMargin=12 borderNoOverlaps=true borderRounding=0 borderStep=1 borderUnit=Meter controlPoints=auto graticule=auto grid=auto legend=auto name=MapMnaziBayhab northArrow=auto paging=continuous ref=r1 scaleBar=auto scope=locked center / scale scopeDetail=646802.61034615175,8856311.5759953968,150 xmax=0.35877862595419846 xmin=0.027989821882951665 ymax=0.98902384414662947 ymin=0.32371064328183174 / component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8 borderFore=#00 borderMargin=12 borderNoOverlaps=true borderRounding=0 borderStep=1 borderUnit=Meter controlPoints=auto graticule=auto grid=auto legend=hide name=MapMnaziBayall northArrow=auto paging=continuous ref=r3 scaleBar=auto scope=locked center / scale scopeDetail=646802.61034615175,8856311.5759953968,150 xmax=0.707379134860051 xmin=0.37659033078880411 ymax=0.98902384414662947 ymin=0.32371064328183174 / component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8 borderFore=#00 borderMargin=12 borderNoOverlaps=true borderRounding=0 borderStep=1 borderUnit=Degree controlPoints=auto graticule=auto grid=auto legend=auto name=Map Africa Mnazi northArrow=auto paging=continuous ref=r6 scaleBar=auto scope=entire component xmax=0.93198992443324935 xmin=0.73047858942065491 ymax=0.98902384414662947 ymin=0.84662172667648694 / /elements /layout Any idea? Thanks. Paulo Cardoso [[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. -- Martin Morgan Computational Biology / Fred Hutchinson Cancer Research Center 1100 Fairview Ave. N. PO Box 19024 Seattle, WA 98109 Location: Arnold Building M2 B169 Phone: (206) 667-2793 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] function to transform response of a formula
Hi, I am now trying to use update.formula from within a function but I am not able to get the result I want. Here is an example f - function(fm, n) { update(fm, n*. ~ .); } If I run fm - formula( y ~ a + b ) f(fm,3) n * y ~ a + b Now when I try to use the formula, n does not exist. Is there a way I can change my function so that n is replaced by its value within the formula created by f? Thanks, Paul [EMAIL PROTECTED] wrote: Its ok. I've just read about update.formula in another message. Paul Paul Emberson wrote: Hi, I am trying to write a function which takes a formula as input and outputs a new formula with a different response while keeping the rest of the formula the same. I.e. respapply : ( y ~ a+b ) - ( f(y) ~ a + b ) I have tried the following but it doesn't work. The terms become invalid as shown below. respapply - function(fm, f) { fm[[2]] - f(eval(fm[[2]])) fm; } fm - formula(y ~ a + b) y - runif(5) newfm - respapply(fm,identity) newfm c(0.552921097259969, 0.939932722365484, 0.62522904924117, 0.899310540175065, 0.877736972644925) ~ a + b terms(newfm) Error in terms.formula(fmapply(fm, identity)) : invalid term in model formula Could someone put me in the right direction of how to correctly write a respapply function as described. Regards, Paul Emberson __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] adding lines to multiple plot
Hi I am trying to add density lines to multiple histograms created using R. I have managed to get all 18 lines on the last histogram in the series, however, i cannot figure out how to get each line appear on the correct histogram plot. I know in Matlab there is a hold function, is there something similar in R? the following is the code i have used to get mutiple plots and then add all the lines to the final plot: ##find unique column names in table variablenames-unique(names(variables)) ## define number of unique names Nvariables-length(variablenames) ##for loop required for labelling of histograms and to tell how many hist to make for(i in 1:Nvariables){ par(mfrow=c(1,1),ask=TRUE) } ##use lapply for dataframes creates hist for each variable and labels corresponding ##important to have this outside of loop lapply(names(variables),function(i)hist(variables[[i]],probability=T,main=paste(Histogram of,i), xlab=paste(i))) for(i in 1:Nvariables){ lines(density(variables[[i]],lwd=2)) } I am pretty sure its a simple explanation, i have just run out of ideas. Thanks gary Watmough PhD Student University of Southamton School of Geography -- View this message in context: http://www.nabble.com/adding-lines-to-multiple-plot-tp18732850p18732850.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] What's the best way to operate R from within Excel?
HI all, Is that the best R link from within Excel currently? Thanks! Patrizio Frederic wrote: have a look at http://sunsite.univie.ac.at/rcom/server/doc/RExcel.html regards, PF 2008/7/30 losemind [EMAIL PROTECTED]: Hi all, How do I operate R from within Excel? I mean, highlight a bunch of cells, and send to R, and do some statistics in R, and return back the numbers and do some plots in R. For example, I have some parameters for Gaussian Random variable, and I would find the most convenient way to send these numbers to R and do some plots... How to do that? Thanks a lot! -- View this message in context: http://www.nabble.com/What%27s-the-best-way-to-operate-R-from-within-Excel--tp18722737p18722737.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/What%27s-the-best-way-to-operate-R-from-within-Excel--tp18722737p18732845.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] R command history -- can it be like Matlab's?
Prof Brian Ripley wrote: A patch to do this was posted on 2007-09-29 by Glenn Davis. Some people not addicted to Matlab find the behaviour very inconvenient and prefer the getline/readline behaviour (triggered by ^R/^S) of Rterm and R on Unixen. On Tue, 29 Jul 2008, losemind wrote: Hi all, In R GUI window, if you use up and down key, you will be able to recall the previous and next command that has been used and stored in the command history cache. But there is one inconvenience: Or an inconvenience of Matlab not shared by R, depending on your preferences. In Matlab, you can type the first a few characters of the command that you previously used, and then press “up key, you will be able to get to that previous command very fast, no matter how long ago it has been used... In R GUI, there is no such functionality. Any thoughts on making R work my productivity? -- Also where do I find good debugger for R? Thanks! -- View this message in context: http://www.nabble.com/R-command-historycan-it-be-like-Matlab%27s--tp18719530p18719530.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. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. HI I am using Windows RGUI... where do I find that patch? Thanks -- View this message in context: http://www.nabble.com/R-command-historycan-it-be-like-Matlab%27s--tp18719530p18732866.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] R -Legality Question about R's Open Source GNU GPL License
whats the license policy of using r as a SaaS with other apps, priced for a fee. I am not sure which license to invoke. regards, ajay [[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] Unexpected line type in lattice plot key on pdf device
L.S., With the code below, on the Windows screen the line types in the key show as solid and dashed as in the graph, and in the pdf file they show as solid in the key and solid and dashed in the graph. I would not expect that, but may be I get something wrong. Gerrit. --- library(lattice) # pdf(pietje.pdf) x-0:10 xyplot((x^0.5)+(x^0.75)~x,type=o,lty=c(1,2), auto.key=list(points=F,lines=T,columns=2, type=o,divide=1)) # dev.off() --- -- Gerrit Draisma Department of Public Health Erasmus MC, University Medical Center Rotterdam Room AE-103 P.O. Box 2040 3000 CA Rotterdam The Netherlands Phone: +31 10 7043124 Fax: +31 10 7038474 http://mgzlx4.erasmusmc.nl/pwp/?gdraisma __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] read XML
Ok, I reach this with setwd(E:/MBayRNP/output) xml.mfd-xmlTreeParse(myfile.xml) str(xml.mfd$doc$children$layout) and get this: layout nameLayout 2/name pagesByX1/pagesByX pagesByY1/pagesByY elements legend refParent=r3 xmax=0.54156171284634758 xmin=0.020151133501259435 ymax=0.31480598161051165 ymin=0.042461931948864044/ component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8 borderFore=#00 borderMargin=12 borderNoOverlaps=true borderRounding=0 borderStep=1 borderUnit=Meter controlPoints=auto graticule=auto grid=auto legend=auto name=MapMnaziBayhab northArrow=auto paging=continuous ref=r1 scaleBar=auto scope=locked center / scale scopeDetail=646802.61034615175,8856311.5759953968,150 xmax=0.35877862595419846 xmin=0.027989821882951665 ymax=0.98902384414662947 ymin=0.32371064328183174/ component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8 borderFore=#00 borderMargin=12 borderNoOverlaps=true borderRounding=0 borderStep=1 borderUnit=Meter controlPoints=auto graticule=auto grid=auto legend=hide name=MapMnaziBayall northArrow=auto paging=continuous ref=r3 scaleBar=auto scope=locked center / scale scopeDetail=646802.61034615175,8856311.5759953968,150 xmax=0.707379134860051 xmin=0.37659033078880411 ymax=0.98902384414662947 ymin=0.32371064328183174/ component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8 borderFore=#00 borderMargin=12 borderNoOverlaps=true borderRounding=0 borderStep=1 borderUnit=Degree controlPoints=auto graticule=auto grid=auto legend=auto name=Map Africa Mnazi northArrow=auto paging=continuous ref=r6 scaleBar=auto scope=entire component xmax=0.93198992443324935 xmin=0.73047858942065491 ymax=0.98902384414662947 ymin=0.84662172667648694/ /elements /layout I don't know how to go further and extract elements listed with str(xml.mfd$doc$children$layout) List of 4 $ name:List of 1 ..$ text: list() .. ..- attr(*, class)= chr [1:2] XMLTextNode XMLNode ..- attr(*, class)= chr XMLNode $ pagesByX:List of 1 ..$ text: list() .. ..- attr(*, class)= chr [1:2] XMLTextNode XMLNode ..- attr(*, class)= chr XMLNode $ pagesByY:List of 1 ..$ text: list() .. ..- attr(*, class)= chr [1:2] XMLTextNode XMLNode ..- attr(*, class)= chr XMLNode $ elements:List of 4 ..$ legend : list() .. ..- attr(*, class)= chr XMLNode ..$ component: list() .. ..- attr(*, class)= chr XMLNode ..$ component: list() .. ..- attr(*, class)= chr XMLNode ..$ component: list() .. ..- attr(*, class)= chr XMLNode ..- attr(*, class)= chr XMLNode - attr(*, class)= chr XMLNode And I need the first two components of elements:List of 4. From those components I need to manipulate xmax and xmin and write a new xml with these parameters changed only. -Original Message- From: Martin Morgan [mailto:[EMAIL PROTECTED] Sent: quarta-feira, 30 de Julho de 2008 13:49 To: Paulo Cardoso Cc: r Subject: Re: [R] read XML Paulo Cardoso [EMAIL PROTECTED] writes: I have a xml exported by Manifold GIS but I'm not being able to import it into R using XLM package. I can library(XML) xml - xmlTreeParse(tmp.xml, useInternal=TRUE) xpathApply(xml, //component/@ymin, xmlValue) [[1]] [1] 0.32371064328183174 [[2]] [1] 0.32371064328183174 [[3]] [1] 0.84662172667648694 so I wonder what specifically your difficulty is? Best, Martin The file have this structure: ?xml version=1.0 encoding=UTF-8 ? - layout nameLayout 2/name pagesByX1/pagesByX pagesByY1/pagesByY - elements legend refParent=r3 xmax=0.54156171284634758 xmin=0.020151133501259435 ymax=0.31480598161051165 ymin=0.042461931948864044 / component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8 borderFore=#00 borderMargin=12 borderNoOverlaps=true borderRounding=0 borderStep=1 borderUnit=Meter controlPoints=auto graticule=auto grid=auto legend=auto name=MapMnaziBayhab northArrow=auto paging=continuous ref=r1 scaleBar=auto scope=locked center / scale scopeDetail=646802.61034615175,8856311.5759953968,150 xmax=0.35877862595419846 xmin=0.027989821882951665 ymax=0.98902384414662947 ymin=0.32371064328183174 / component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8 borderFore=#00 borderMargin=12 borderNoOverlaps=true borderRounding=0 borderStep=1 borderUnit=Meter controlPoints=auto graticule=auto grid=auto legend=hide name=MapMnaziBayall northArrow=auto paging=continuous ref=r3 scaleBar=auto scope=locked center / scale scopeDetail=646802.61034615175,8856311.5759953968,150 xmax=0.707379134860051 xmin=0.37659033078880411 ymax=0.98902384414662947 ymin=0.32371064328183174 / component background=auto border=none borderDegMinSec=false borderEachPage=true borderFont=Tahoma, 8
[R] odds ratios in multiway tables (stratified)
Hi, does anyone know of a function to calculate odds ratios in multiway tables (stratified) (+ the other usual statistics involved) i mean: say we have a table r*c*d, For every d (depth) we have a r*c table, and in this table the odds ratio's are calculated for every 2*2 subtable in it. logically this function would look like): ORs(multiwaytable) or ORs(data$var1r,data$var2c,data$var3d) (eg. not taking the lot together, keeping the paradox of simpson in mind) mvg, Wim __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] FFT - (STATS) - is this correct?
#ts with a freq=1 d - ts(x) #it seems that this is an oscillating signal of ~ a day plot(d) #spectrogram which shows that the main frequency component is ~ 0.7. this translates to about a day (1.3 or so) sec.pgram(d) On Wed, Jul 30, 2008 at 7:14 AM, [EMAIL PROTECTED] wrote: Hello, I have calculated the fourier transform of the series enclosed at the end of this message, by doing: library(stats) x - readLines(file1.txt) x.num - as.numeric(x) ft.x.num - fft(x.num) My question is: why is the first value (Real) of ft.x.num that big? (954.833870) all the other values are much smaller. Am I doing something wrong? Could you please help me to understand that? Many thanks, Renata 2.24791 6.39824 7.43533 7.21367 11.2164 7.29183 9.72807 12.8445 12.4819 8.18952 6.38345 9.98463 6.25724 7.97327 8.9676 8.27709 14.8272 13.4908 11.876 11.4889 11.3161 9.79778 8.09873 4.43935 5.30657 9.37819 0 8.09507 10.9567 10.5478 12.6661 13.8612 14.025 13.9403 11.5847 9.50861 7.81196 5.4 5.27313 4.16159 3.83932 8.95892 11.9548 12.7598 11.6816 13.3388 13.1956 9.50887 12.4671 11.2608 12.6553 5.63253 4.18556 4.47097 9.13142 5.29101 11.3582 7.5489 13.0371 9.26487 11.6458 6.26179 10.4051 11.7282 9.36171 10.7723 4.90151 4.25747 6.95437 6.17832 11.59 13.894 10.8935 8.19078 6.27219 6.74875 10.076 6.47078 11.1408 6.48286 10.4232 9.23548 11.199 7.97828 13.1261 12.1624 7.90476 11.7495 14.0312 9.97212 11.3685 12.6093 4.68484 4.72131 5.10963 8.1693 8.21239 10.6743 5.39084 11.1944 12.4415 8.0419 5.62567 12.2756 0 - Email sent from www.virginmedia.com/email Virus-checked http://www.virginmedia.com/emailVirus-checked using McAfee(R) Software and scanned for spam __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Let's not spend our time and resources thinking about things that are so little or so large that all they really do for us is puff us up and make us feel like gods. We are mammals, and have not exhausted the annoying little problems of being mammals. -K. Mullis [[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] adding lines to multiple plot
Gary W g.watmough at gmail.com writes: Hi I am trying to add density lines to multiple histograms created using R. I have managed to get all 18 lines on the last histogram in the series, however, i cannot figure out how to get each line appear on the correct histogram plot. I know in Matlab there is a hold function, is there something similar in R? ##find unique column names in table variablenames-unique(names(variables)) ## define number of unique names Nvariables-length(variablenames) for(i in 1:Nvariables){ par(mfrow=c(1,1),ask=TRUE) } previous loop is a little weird -- it has exactly the same result as just running the command inside once. Labeling with the numeric values is a bit of a pain. If you don't need them you can just do lapply(variables, function(v) { hist(v,prob=TRUE) lines(density(v),lwd=2) }) If you need the labels you can either do mapply(function(v,i) { hist(v,prob=TRUE,main=paste(Histogram of,i),xlab=i) lines(density(v),lwd=2) }, variables, 1:Nvariables) Or it might be easier to just do the whole thing with a for loop: for (i in 1:Nvariables) { hist(variables[[i]],prob=TRUE,main=paste(Histogram of,i),xlab=i) lines(density(variables[[i]]),lwd=2) } Ben Bolker __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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 -Legality Question about R's Open Source GNU GPL License
on 07/30/2008 08:39 AM Ajay ohri wrote: whats the license policy of using r as a SaaS with other apps, priced for a fee. I am not sure which license to invoke. regards, ajay See this post: https://stat.ethz.ch/pipermail/r-help/2008-June/165906.html HTH, Marc Schwartz __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] model mix problem. FALSE CONVERGENCE
Hi R users I try to use the lme but I can´t! My script is (some words in french, sorry!!): rm(list=ls(all=TRUE)) #Efface tous les objets en mémoire pour éviter des erreurs library(MASS) #Chargement des Librairies library(car) library(Hmisc) library(tkWidgets) library(svDialogs) library(multtest) library(nlme) #Rep - C:/Documents and Settings/U3M/Bureau/steph/Scripts R/ Rep - C:/Documents and Settings/rafa/Mis documentos/metabolomics/Scripts R/Modèles Mixtes/ # Choix du fichier à traiter source(sprintf(%sinfile2bis.q,Rep)) para-infile2bis() # Ouvre une petite interface permettant de sélectionner le fichier # que l'on veut traiter Fic - para$fichier # fic est le fichier à traiter pat - para$pat # Répertoire de résultats CLASSE - noquote(para$classe[1:2]) # Facteurs à étudier .method-which(para$checks2!=F) #Méthode d'ajustement des p-values # Vérification qu'on est bien ds le bon répertoire de travail if ( getwd()!=dirname(Fic[1]) ) setwd(dirname(Fic[1])) ## Quelques conditions à vérifier if (sum(CLASSE==)=1) { guiDlgMessage(Il faut spécificier deux variables catégorielles., title = ERROR, type = ok, icon = c(error), parent = 0) stop(Il faut spécificier deux variables catégorielles) } if (sum(para$checks1==c(T,T))==2) { guiDlgMessage(Il ne faut cocher qu'une seule case pour la ligne Transformation des données., title = ERROR, type = ok, icon = c(error), parent = 0) stop(Il ne faut cocher qu'une seule case pour la ligne Transformation des données) } if (length(which(para$checks2)==T)1) { guiDlgMessage(Vous ne pouvez choisir qu'une seule méthode de correction des p-values, ne cochez qu'une seule case., title = ERROR, type = ok, icon = c(error), parent = 0) stop(Error : vous ne pouvez choisir qu'une seule méthode de correction des p-values )} ##Manipulation sur le fichier de données titi - read.table(Fic[2],header=T,sep=\t) # Lecture du fichier Protocole indiv - as.character(titi[,1])#Identifiant des individus Subject - as.factor(titi[,1]) n - dim(titi)[1] #Nb individus toto1 - read.table(Fic[1],header=T,sep=\t) # Lecture du fichier de données ions - as.character(toto1[,1]) #Identifiant des ions ## La matrice des Intensités if (sum(para$checks1==c(T,F))==2) { toto - log2(t(toto1[,-c(1:(dim(toto1)[2]-n))])+1) } if (sum(para$checks1==c(F,T))==2) { toto - t(toto1[,-c(1:(dim(toto1)[2]-n))]) } if (sum(para$checks1==c(F,F))==2) { toto - t(toto1[,-c(1:(dim(toto1)[2]-n))]) } nvar - dim(toto)[2] #Nb variables = Nb ions if (is.numeric(toto)==F) { guiDlgMessage(Problème de fichier :\r\n vérifier vos données., title = ERROR, type = ok, icon = c(error), parent = 0) stop(Nombre d'individus différents dans les deux fichiers : vérifier vos données)} Facteurs - titi[,-1] #Les facteurs #Création d'un répertoire où enregistrer les résultats if (any(dir(getwd())==strsplit(pat,/))==F) { if (pat!=) { dir.create(file.path(getwd(),pat)) } } #ANOVA 2 voies v1 - Facteurs[[CLASSE[1]]] v2 - Facteurs[[CLASSE[2]]] if (is.null(v1) | is.null(v2)) { guiDlgMessage(Vous n'avez pas spécifier un facteur catégoriel correct.\r\n\r\nAttention, il faut que le nom du facteur que vous entrez \r\ndans l'interface et celui du fichier protocole soient \r\nexactement les mêmes.\r\n\r\nR est sensible à la case., title = ERROR, type = ok, icon = c(error), parent = 0) } ## ANOVA 2 facteurs Resultats=NULL Res=NULL i=0 while(i!=length(ions)) { i=i+1 myion=toto[,i] mixed=lme(myion ~ v1*v2, random= ~ 1 | Subject/v1,method=REML) ## effet aléatoire sujet(v1) #summary(mixed) #anova(mixed) zz=anova(mixed) Res - data.frame(ions[i],toto1[i,2:(dim(toto1)[2]-n)],t(zz[-1,4]),toto1[i,c((dim(toto1)[2]-n+1):dim(toto1)[2])]) Resultats - rbind(Resultats,Res) } if (i!=length(ions)) { while(i!=length(ions)) { i=i+1 myion=toto[,i] mixed=lme(myion ~ v1*v2, random= ~ 1 | Subject/v1,method=REML) ## effet aléatoire sujet(v1) zz=anova(mixed) Res - data.frame(ions[i],toto1[i,2:(dim(toto1)[2]-n)],t(zz[-1,4]),toto1[i,c((dim(toto1)[2]-n+1):dim(toto1)[2])]) Resultats - rbind(Resultats,Res) }} if (i!=length(ions)) { while(i!=length(ions)) { i=i+1 myion=toto[,i] mixed=lme(myion ~ v1*v2, random= ~ 1 | Subject/v1,method=REML) ## effet aléatoire sujet(v1) zz=anova(mixed) Res -
Re: [R] adding lines to multiple plot
Hi ben Thanks for that, the density lines have now worked, however i was hoping that the labels would be the names of the columns in my original data set not numeric. any advice how to do this? gary w Ben Bolker wrote: ##find unique column names in table variablenames-unique(names(variables)) ## define number of unique names Nvariables-length(variablenames) for(i in 1:Nvariables){ par(mfrow=c(1,1),ask=TRUE) } previous loop is a little weird -- it has exactly the same result as just running the command inside once. Labeling with the numeric values is a bit of a pain. If you don't need them you can just do lapply(variables, function(v) { hist(v,prob=TRUE) lines(density(v),lwd=2) }) If you need the labels you can either do mapply(function(v,i) { hist(v,prob=TRUE,main=paste(Histogram of,i),xlab=i) lines(density(v),lwd=2) }, variables, 1:Nvariables) Or it might be easier to just do the whole thing with a for loop: for (i in 1:Nvariables) { hist(variables[[i]],prob=TRUE,main=paste(Histogram of,i),xlab=i) lines(density(variables[[i]]),lwd=2) } Ben Bolker __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/adding-lines-to-multiple-plot-tp18732850p18734458.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] Most often pairs of chars across grouping variable
Hi Marc, many thanks, that is exactly what I was looking for. Best, Sven - Original Nachricht Von: Marc Schwartz [EMAIL PROTECTED] An: [EMAIL PROTECTED] Datum: 29.07.2008 17:15 Betreff: Re: [R] Most often pairs of chars across grouping variable on 07/29/2008 09:51 AM [EMAIL PROTECTED] wrote: Hi list, is there a package or function to compute the frequencies of pairs of chars in a variable across a grouping variable? Eg: d - data.frame(ID=gl(2,3), F=c(A,B,C,A,C,D)) d ID F 1 1 A 2 1 B 3 1 C 4 2 A 5 2 C 6 2 D Now I want to summarize the frequencies of all pairs A-B, A-C, A-D, B-C, B-D, C-D across ID: A B C D A - 1 2 1 B - - 1 0 C - - - 1 here, the combination A-C is most frequent. The real problem behind that is that 'F' codes diagnoses and I search for the most often pairs of diagnoses. Thanks, Sven I suspect that there might be something over in Bioconductor, but here is one approach: table(data.frame(t(do.call(cbind, tapply(d$F, d$ID, function(x) combn(as.character(x), 2)) X2 X1 B C D A 1 2 1 B 0 1 0 C 0 0 1 See ?combn to create the initial pairs from the data. This is done on a per ID basis using tapply. The result is transposed into a data frame and then table() is used to create the cross tabulation of the results. HTH, Marc Schwartz __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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 -Legality Question about R's Open Source GNU GPL License
The limit of use is that you cannot profit from it. It is Open Source. From: [EMAIL PROTECTED] [EMAIL PROTECTED] On Behalf Of Ajay ohri [EMAIL PROTECTED] Sent: Wednesday, July 30, 2008 9:39 AM To: r-help@r-project.org Subject: [R] R -Legality Question about R's Open Source GNU GPL License whats the license policy of using r as a SaaS with other apps, priced for a fee. I am not sure which license to invoke. regards, ajay [[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 -Legality Question about R's Open Source GNU GPL License
Absolutely FALSE. Read this FAQ and the following 3: http://www.fsf.org/licensing/licenses/gpl-faq.html#DoesTheGPLAllowMoney Let's not spread FUD. Marc Schwartz on 07/30/2008 08:50 AM Stevens, Martin Henry H. Dr. wrote: The limit of use is that you cannot profit from it. It is Open Source. From: [EMAIL PROTECTED] [EMAIL PROTECTED] On Behalf Of Ajay ohri [EMAIL PROTECTED] Sent: Wednesday, July 30, 2008 9:39 AM To: r-help@r-project.org Subject: [R] R -Legality Question about R's Open Source GNU GPL License whats the license policy of using r as a SaaS with other apps, priced for a fee. I am not sure which license to invoke. regards, ajay __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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 -Legality Question about R's Open Source GNU GPL License
Hi, Stevens, Martin Henry H. Dr. wrote: The limit of use is that you cannot profit from it. It is Open Source. I am not sure what you mean exactly. If you mean that you can not earn any money selling free software (in terms of the GPL2, which is R's licence), this seems to be not the case: http://www.fsf.org/licensing/essays/selling.html Best, Roland __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Percent Change After Each Interval
Hi, I have a data set (attached, and which I've asked about before) containing countries, prices and dates. I am trying to find the mean and median (by country) percentage change of each price change. For example: Date Australia 6/30/07 2 3/31/07 2 11/30/06 2 5/2/06 2 1/11/06 2 8/5/05 2 7/31/05 2 4/30/05 1.5 1/31/05 1.5 1/3/05 1.5 1/2/054 So for this period for Australia, there are 2 price changes. The first change is a 25% change, and the second is 266.66%. If this were all the data there was, the mean percentage change is ~146% and the median would be the same. I was wondering if anyone knew a way that would collect the percentage change at each price change and then calculate the mean and median of those percentages, and could do this for a data set with a lot of countries (so the output would be broken up by country). Any help would be appreciated! Thanks! Jia Ying Mei __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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 -Legality Question about R's Open Source GNU GPL License
now which license to use? it is bad enough explaining SaaS (software as a service), and open source and data mining to lawyers, without the experts fighting it as well. and who pays for the cloud computing expenses for me then if there is no money in it. cloud computing doesnt exist in India right now from where I am writing this? regards, ajay decisionstats.com On 7/30/08, Roland Rau [EMAIL PROTECTED] wrote: Hi, Stevens, Martin Henry H. Dr. wrote: The limit of use is that you cannot profit from it. It is Open Source. I am not sure what you mean exactly. If you mean that you can not earn any money selling free software (in terms of the GPL2, which is R's licence), this seems to be not the case: http://www.fsf.org/licensing/essays/selling.html Best, Roland __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Mixed effects model where nested factor is not the repeated across treatments lme???
Hi Miki, I just got the same problem with you couple hours ago. Rusers (Anna, and Mark {thank you guys}) provide me a vary valuable information. link to following address. http://www.nabble.com/Tukey-HSD-(or-other-post-hoc-tests)-following-repeated-measures-ANOVA-td17508294.html#a17559307 for the A vs. B, A vs. C You could install and download the multcomp package and perform the post hoc test such as summary(glht(lmel,linfct=mcp(treatment=Tukey))) hopefully it helps Chunhao Quoting M Ensbey [EMAIL PROTECTED]: Hi, I have searched the archives and can't quite confirm the answer to this. I appreciate your time... I have 4 treatments (fixed) and I would like to know if there is a significant difference in metal volume (metal) between the treatments. The experiment has 5 blocks (random) in each treatment and no block is repeated across treatments. Within each plot there are varying numbers of replicates (random) (some plots have 4 individuals in them some have 14 and a range in between). NOTE the plots in one treatment are not replicated in the others. So I end up with a data.frame with 4 treatments repeated down one column (treatment=A, B, C, D), 20 plots repeated down the next (block= 1 to 20) and records for metal volume (metal- 124 of these) I have made treatment and block a factor. But haven't grouped them (do I need to and how if so) The main question is in 3 parts: 1. is this the correct formula to use for this situation: lme1-lme(metal~treatment,data=data,random=~1|block) (or is lme even the right thing to use here?) I get: summary(lme1) Linear mixed-effects model fit by REML Data: data AIC BIClogLik 365.8327 382.5576 -176.9163 Random effects: Formula: ~1 | block (Intercept) Residual StdDev: 0.4306096 0.9450976 Fixed effects: Cu ~ Treatment Value Std.Error DF t-value p-value (Intercept) 5.587839 0.2632831 104 21.223688 0. *** TreatmentB -0.970384 0.3729675 16 -2.601792 0.0193 *** TreatmentC -1.449250 0.3656351 16 -3.963651 0.0011 *** TreatmentD -1.319564 0.3633837 16 -3.631323 0.0022 *** Correlation: (Intr) TrtmAN TrtmCH TreatmentB -0.706 TreatmentC -0.720 0.508 TreatmentD -0.725 0.511 0.522 Standardized Within-Group Residuals: Min Q1 Med Q3 Max -2.85762206 -0.68568460 -0.09004478 0.56237152 3.20650288 Number of Observations: 124 Number of Groups: 20 2. if so how can I get p values for comparisons between every group... ie is A different from B, is A different from C, is A different from D, is B different from C, is B different from D etc... is there a way to get all of these instead of just is A different from B, is A different from C, is A different from D which summary seems to give? 3. last of all what is the best way to print out all the residuals for lme... I can get qqplot(lme1) is there a pre-programmed call for multiple diagnostic plots like in some other functions... Thankyou so Much for your time It is much appreciated ;-) Miki [[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.
[R] Rprintf will not build in my C++ compiler
I have searched through the threads and Rprintf causing a build error dosen't seem to be a problem for anyone else. And I've read through R Extensions and An Introduction to the .C Interface to R and there doesn't seem to be any troubleshooting for my problem. My code is straight from An Introduction to the .C Interface to R pg. 3. And my compiler is VC++ 2005 Express -- #include R.h void hello( int *n ) { int i ; for( i = 0 ; i *n ; i++ ) { Rprintf( Hello, world!\n ) ; } } -- When I try to build this code, I recieve 2 error massages, error LNK2019: unresolved external symbol _Rprintf referenced in function void _cdecl hello(int *n) (?hello@@[EMAIL PROTECTED]) fatal error LNK1120: 1 unresolved externals To be honest, I'm not exactly sure what these errors mean, I'm still learning C++. Any thoughts would be appreciated. -- View this message in context: http://www.nabble.com/Rprintf-will-not-build-in-my-C%2B%2B-compiler-tp18735205p18735205.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] R -Legality Question about R's Open Source GNU GPL License
on 07/30/2008 10:35 AM [EMAIL PROTECTED] wrote: now which license to use? it is bad enough explaining SaaS (software as a service), and open source and data mining to lawyers, without the experts fighting it as well. and who pays for the cloud computing expenses for me then if there is no money in it. cloud computing doesnt exist in India right now from where I am writing this? As I noted in my reply, there is nothing preventing you using FOSS to create a value added service, from which you can generate profitable income. If there was, Red Hat would not be a public company with shareholders, Canonical (Ubuntu's commercial sponsor) would not exist and Dell would not be selling computers with Ubuntu pre-installed. Whether anyone will actually pay you for your service is another question and a business risk that you have to evaluate. That being said, if you are planning to start up a company based upon the use of FOSS as your foundation, get yourself a lawyer familiar with it and fire any lawyer that you are currently using who is not. There are lawyers with the requisite experience in both FOSS and IP. This is not the proper forum to seek business development advice. Marc Schwartz __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Axes in perspective plot - persp()
All, I'm making some plots with the persp() function and am having trouble sorting out the following: - How does one avoid the axes label overlapping the tick values? - Is doesn't seem possible to independently control the number of ticks of the x,y, and z-axes, e.g., I'd like say only 4 ticks on the y axes but 10 on the other two. - for my function (although it doens't happen for the reproducible example below unfortunately) the origin of the x and y tick values seem to overlap, is there any way to avoid this? Example below. theta - seq(.1, 10, length = 30) rho - seq(0, .99, length = 30) f - function(theta, rho) { theta + rho^2 } Z - outer(theta, rho, f) persp(theta, rho, Z, expand = 0.5, col = lightblue, ticktype = detailed, nticks = 10) Thanks, David __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Rprintf will not build in my C++ compiler
That is a linker (not compiler) message, and you apparently forgot to link against R.dll. See README.packages in the R distribution for how to use VC++ with R under Windows (which is neither recommended nor supported). Three other comments. 1) See the posting guide. R-devel is the list for non-R programming questions. 2) See the posting guide. You didn't show how you compiled your code nor what exact command gave that error message. 3) See 'Writing R Extensions'. For that code to be any use with R, it has to have a C and not C++ entry point 'hello'. On Wed, 30 Jul 2008, nmarti wrote: I have searched through the threads and Rprintf causing a build error dosen't seem to be a problem for anyone else. And I've read through R Extensions and An Introduction to the .C Interface to R and there doesn't seem to be any troubleshooting for my problem. Well, you _are_ using an unsupported compiler/linker. My code is straight from An Introduction to the .C Interface to R pg. 3. Which is what? (Not an official manual.) And my compiler is VC++ 2005 Express -- #include R.h void hello( int *n ) { int i ; for( i = 0 ; i *n ; i++ ) { Rprintf( Hello, world!\n ) ; } } -- When I try to build this code, I recieve 2 error massages, error LNK2019: unresolved external symbol _Rprintf referenced in function void _cdecl hello(int *n) (?hello@@[EMAIL PROTECTED]) fatal error LNK1120: 1 unresolved externals To be honest, I'm not exactly sure what these errors mean, I'm still learning C++. Any thoughts would be appreciated. -- View this message in context: http://www.nabble.com/Rprintf-will-not-build-in-my-C%2B%2B-compiler-tp18735205p18735205.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. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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 -Legality Question about R's Open Source GNU GPL Licen
In this midst of all this debate, can I try a simple question? Have the enforceability and/or interpretation of the GPL ever been tested in court? If so, then are there any references to where one can read about the case (or cases)? With thanks, Ted. E-Mail: (Ted Harding) [EMAIL PROTECTED] Fax-to-email: +44 (0)870 094 0861 Date: 30-Jul-08 Time: 17:19:20 -- XFMail -- __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] R -Legality Question about R's Open Source GNU GPL License
well, i am planning to test rattle (r gui) or even R on a cloud computer. IMO SAS (software ) scores over R because it handles bigger files more efficiently on SAME local hardware. but prices a huge premium on licenses. with R and a cloud, you pay for time spent (1+profit P). cloud ramps up processing power as needed. data mining to the masses. got 400 million rows and no money to work as a stats consultant. pay per use. and i am ready to give it away to greenpeace , whatever.. .just not to any big corp who patents it first. the question was which license to use, and i got two answers . so that was the clarification. is this a business development plan maybe. but is also a r development plan which is much better algols than any other software.but still lacks acceptance . and now for finding someone enough to sponser the cloud development time, without hoping for lazy royalty assets) thanks for your help and support. regards, ajay. the framework is on decisionstats dot com On 7/30/08, Marc Schwartz [EMAIL PROTECTED] wrote: on 07/30/2008 10:35 AM [EMAIL PROTECTED] wrote: now which license to use? it is bad enough explaining SaaS (software as a service), and open source and data mining to lawyers, without the experts fighting it as well. and who pays for the cloud computing expenses for me then if there is no money in it. cloud computing doesnt exist in India right now from where I am writing this? As I noted in my reply, there is nothing preventing you using FOSS to create a value added service, from which you can generate profitable income. If there was, Red Hat would not be a public company with shareholders, Canonical (Ubuntu's commercial sponsor) would not exist and Dell would not be selling computers with Ubuntu pre-installed. Whether anyone will actually pay you for your service is another question and a business risk that you have to evaluate. That being said, if you are planning to start up a company based upon the use of FOSS as your foundation, get yourself a lawyer familiar with it and fire any lawyer that you are currently using who is not. There are lawyers with the requisite experience in both FOSS and IP. This is not the proper forum to seek business development advice. Marc Schwartz __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] FOURIER TRANSFORM HELP
Hello, I have a series and I need to run a Fourier Transform for that series. I have done that using the function fft from stats package. However I am not sure whether the result I am getting is correct or not. Seems that the first value of the Fourier Transform list is the sum of all elements of the given series and all the following numbers represent a palindromic series for some how. I have never used a Fourier Transform before and I don't know whether that is how it should work or not. Could anyone help me with that or give me some suggestions, please? Thank you ever so much, Renata - Email sent from www.virginmedia.com/email Virus-checked using McAfee(R) Software and scanned for spam __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] ~ . help
At 08:44 30/07/2008, [EMAIL PROTECTED] wrote: Hello, What the tilde and dot means? I believe is something to do with formula, but how do they work? You are already half way there ?formula should help you find out what ~ means ?update.formula should help you find out what . means in the context of formulae An example: (fk5 ~ ., size = 10) Do you know what the fk5 ~ . means? Thank you! Renata - Email sent from www.virginmedia.com/email Virus-checked using McAfee(R) Software and scanned for spam Michael Dewey http://www.aghmed.fsnet.co.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] R -Legality Question about R's Open Source GNU GPL Licen
Ted, yes, there were a couple of cases, both in Europe and in the US. See more here: http://www.softwarefreedom.org/ As far as I can remember, all lawsuits ended with an agreement, and the publication of the source code, of course. Best, Gabor On Wed, Jul 30, 2008 at 05:19:31PM +0100, Ted Harding wrote: In this midst of all this debate, can I try a simple question? Have the enforceability and/or interpretation of the GPL ever been tested in court? If so, then are there any references to where one can read about the case (or cases)? With thanks, Ted. E-Mail: (Ted Harding) [EMAIL PROTECTED] Fax-to-email: +44 (0)870 094 0861 Date: 30-Jul-08 Time: 17:19:20 -- XFMail -- __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Csardi Gabor [EMAIL PROTECTED]MTA RMKI, ELTE TTK __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Re creating Procrustes Plot in Lattice
On Wed, 2008-07-30 at 04:59 -0700, Andrewjohnclose wrote: Hi, I have been trying to create a function to generate a Procrustes plot, generated from package vegan in lattice. standard vegan code as follows library(vegan) pro=protest(P1, P8, permutations=4999,choices=1:4) plot(pro) Now, here is the code for the function that I have failed to get to work properly. panel.procrustes=function(x,y) }Pro=protest(x,y,permutations=4999,choices=1:4) Proplot=plot(Pro) } xyplot(P1[1:4]~P8[1:4],panel=panel.procrustes) I can generate an empty plot, but not much else - hope someone can help and point out the obvious! Kind regards Andrew The obvious thing is that whole thing is wrong! ;-) What's wrong with the standard plot? You are trying to mix base (standard) graphics functions with grid/lattice graphics and this is not possible (well Ok there is package gridBase). You'll have to start doing the plotting from scratch in panel.procrustes. You might get some ideas of how to do this by looking at the ordixyplot functions and panel functions in current vegan that implement lattice graphics plots for ordiplot objects. I'm not sufficiently familiar with Lattice yet to advise how to go about producing a panel function, but the basic elements are: * draw the points from x$Yrot[, 1:2] * draw the arrows from x$Yrot[, 1:2] to x$X[, 1:2] * draw the origin - equivalent of abline(h = 0) and abline(v = 0) * draw the rotation involved in the Procrustes analysis: abline(0, tan(acos(x$rotation[1, 1])) and abline(0, 1/tan(acos(-x $rotation[1, 1])) So you'll need the Lattice equivalents of abline and then work out how to pass the X, Yrot and rotation components to your panel function. This is the bit I'm not clear on but look at ordixyplot and panel.ordi for inspiration. Give it a go, but if you get stuck then mail me back privately (note I am moving house at the weekend so I'm not going to get back to you any time real soon!) or post a message on the vegan development website: https://r-forge.r-project.org/forum/forum.php?forum_id=194 and Jari may be able to help you - I might also chip in there once I unpack my belongings and get my head round how to pass this stuff around in lattice... G -- %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% 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.
[R] OT: Data mining on demand .Using cloud computers.
Dear Lists, There are many softwares (with many passionate adherents). Some of them are very good upto say 2 million rows but lose steam after that despite having very good focus in innovating algorithms. Some of them are very good on same PC for much more data but become comfortable with the copyrights to innovate on algorithms. I am taing the risk of proposing the Ohri framework for creating R Rattle GUI (can be placed by any analytical software) in a cloud computer . With pay per usage of processing power.And very user friendly to analysts who did not pay for masters degree.or to small consultants. If you are a small academic or a consultant who has dreamt of lot more processing power, here is a framework. It may be totally crap, but the intention is to take data mining to the common masses. Its only fair to pay per usage.Why pay for software , when on your coffee break. Even if you are poor.Especially so. Thanks for reading this. Ajay Ohri http://decisionstats.com/wp-content/uploads/2008/07/ohri-framework.gif Please zoom to view details. Please comment using the comments section. [[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] bug in 'margins' behavior in reshape - cast
according to the documentation of the cast function in the reshape function, I would expect this bit of code from the examples to calculate marginal means over only the 'diet' variable. #Chick weight example names(ChickWeight) - tolower(names(ChickWeight)) chick_m - melt(ChickWeight, id=2:4, na.rm=TRUE) cast(chick_m, diet + chick ~ time, mean, margins=diet) But, summary(cast(subset(chick_m, time == 0), diet + chick ~ time, mean, margins=diet)) returns: dietchick 0 1:21 (all) : 4 Min. :39.00 2:11 18 : 1 1st Qu.:40.85 3:11 16 : 1 Median :41.00 4:11 15 : 1 Mean :41.05 (all): 0 13 : 1 3rd Qu.:42.00 9 : 1 Max. :43.00 (Other):45 which shows that it calculated margins on the 'chick' column as well. this behavior causes great problems for me when in my data one of the columns is a non-factor column, eg a Date, but the unrequested margining behavior turns that column into a factor. am I missing something? Thanks, Mike -- View this message in context: http://www.nabble.com/bug-in-%27margins%27-behavior-in-reshape---cast-tp18737649p18737649.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] R -Legality Question about R's Open Source GNU GPL License
On Wed, 2008-07-30 at 09:50 -0400, Stevens, Martin Henry H. Dr. wrote: The limit of use is that you cannot profit from it. It is Open Source. I think you mean you are unlikely to profit from it if you base your business model on selling the product and the product is the code; because it is GPL you have to make the source available and so anyone could take your source and implement a rival product and probably undercut you as they don't have to employ any developers... There is absolutely nothing against profiting from Open Source. Novel is doing rather nicely these days (albeit somewhat to do with the Microsoft pact), as is RedHat and a whole plethora of other open source ventures. But these guys tend to sell support and services for the code they give away free (as in beer and speech) and don't make money of the code itself. G From: [EMAIL PROTECTED] [EMAIL PROTECTED] On Behalf Of Ajay ohri [EMAIL PROTECTED] Sent: Wednesday, July 30, 2008 9:39 AM To: r-help@r-project.org Subject: [R] R -Legality Question about R's Open Source GNU GPL License whats the license policy of using r as a SaaS with other apps, priced for a fee. I am not sure which license to invoke. regards, ajay [[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. -- %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% 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.
[R] Hello,
Hello, A newbie to R. I am trying to use the exonmap package in R. According to the docs, the xmapDatabase() command should read the config file with all the connection parameters and connect to the DB. But i get the error shown below xmapDatabase(Human) Error in mysqlNewConnection(dbDriver(drv), ...) : RS-DBI driver: (could not connect [EMAIL PROTECTED] on dbname NA Error:Access denied for user 'cagadmin'@'cdev.cag.chop.edu' to database 'NA' ) when i connect to db using dbConnect() it works fine. conn-dbConnect(drv=MySQL,username=cagadmin ) Anybody who can shed some light on whats going on here? thank you all kiran Kiran Annaiah Center for Applied Genomics Informatics Children's Hospital of Philadelphia 267-426-9355 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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 -Legality Question about R's Open Source GNU GPL License
On Wed, 2008-07-30 at 21:05 +0530, [EMAIL PROTECTED] wrote: now which license to use? Use whatever you or your company want to use. As long as it is in compliance with GPL2 (as that is the licence R currently uses) then you are fine. As to whether what you intend to do is in compliance with the GPL2, then you'll find only lay-person comments on this list (as far as I know there are know lawyers lurking on the list that have raised their heads...), some informed because they have gone through similar procedures in their work place/business and others less well informed. If this is really important to you/your business, then consult a lawyer. R Core are not lawyers and as such you won't see them contributing to threads like this, other than to answer the basics (e.g. the what licence is R released under type question). it is bad enough explaining SaaS (software as a service), and open source and data mining to lawyers, without the experts fighting it as well. I doubt anyone contributing to this thread would call themselves an expect in this field, and they are not fighting, just offering opinions - but I wouldn't base my business model on these opinions on GPL, licensing etc. You need a lawyer for that, preferably one that is familiar with the computing industry and software licences. This list is not the place to solicit such advice, as you have found out. G and who pays for the cloud computing expenses for me then if there is no money in it. cloud computing doesnt exist in India right now from where I am writing this? regards, ajay decisionstats.com On 7/30/08, Roland Rau [EMAIL PROTECTED] wrote: Hi, Stevens, Martin Henry H. Dr. wrote: The limit of use is that you cannot profit from it. It is Open Source. I am not sure what you mean exactly. If you mean that you can not earn any money selling free software (in terms of the GPL2, which is R's licence), this seems to be not the case: http://www.fsf.org/licensing/essays/selling.html Best, Roland __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] bug in 'margins' behavior in reshape - cast
On Wed, Jul 30, 2008 at 11:47 AM, mfrumin [EMAIL PROTECTED] wrote: according to the documentation of the cast function in the reshape function, I would expect this bit of code from the examples to calculate marginal means over only the 'diet' variable. #Chick weight example names(ChickWeight) - tolower(names(ChickWeight)) chick_m - melt(ChickWeight, id=2:4, na.rm=TRUE) cast(chick_m, diet + chick ~ time, mean, margins=diet) But, summary(cast(subset(chick_m, time == 0), diet + chick ~ time, mean, margins=diet)) returns: dietchick 0 1:21 (all) : 4 Min. :39.00 2:11 18 : 1 1st Qu.:40.85 3:11 16 : 1 Median :41.00 4:11 15 : 1 Mean :41.05 (all): 0 13 : 1 3rd Qu.:42.00 9 : 1 Max. :43.00 (Other):45 which shows that it calculated margins on the 'chick' column as well. this behavior causes great problems for me when in my data one of the columns is a non-factor column, eg a Date, but the unrequested margining behavior turns that column into a factor. am I missing something? Hi Mike, I'm not sure what you want - if you want margins at the diet level, then you have to margin over all of the chicks at that level, which is then displayed as (all). Maybe you want margin = grand_row ? Hadley -- http://had.co.nz/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] odds ratios in multiway tables (stratified)
on 07/30/2008 08:48 AM Wim Bertels wrote: Hi, does anyone know of a function to calculate odds ratios in multiway tables (stratified) (+ the other usual statistics involved) i mean: say we have a table r*c*d, For every d (depth) we have a r*c table, and in this table the odds ratio's are calculated for every 2*2 subtable in it. logically this function would look like): ORs(multiwaytable) or ORs(data$var1r,data$var2c,data$var3d) (eg. not taking the lot together, keeping the paradox of simpson in mind) mvg, Wim In ?mantelhaen.test, there is some code in the examples using the UCBAdmissions data set. There is also code for the Woolf test in the same example. In addition, there is similar code in the 'vcd' and 'rmeta' CRAN packages. HTH, Marc Schwartz __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] best quad core configuration?
I am purchasing a quad-core 64-bit system. My proposed configuration is an intel core duo quad with 8Gb memory and an ubuntu OS. I'm choosing ubunto because I have good local support, but it doesn't seem as well supported as debian for R. Will ubuntu limit me in any significant way? I have noticed a bias towards AMD machines among R users - are there compelling reasons to go with an equivalent AMD system instead? Will I be able to use amd64 binaries on this system, or would I have to compile everything myself? Would it difficult to install Intel MKL 10.0 BLAS and LAPACK libraries on this machine? Would it be difficult to run both 32-bit and 64-bit versions of R on this machine? The most computationally-intensive thing I will be using the machine for is large MCMC simulations, probably using multiple instances of LinBUGS. Any advice on configuring by machine for maximum speed for these simulations? Thanks, Alan Swanson [[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] Re creating Procrustes Plot in Lattice
On Wednesday 30 July 2008, Gavin Simpson wrote: On Wed, 2008-07-30 at 04:59 -0700, Andrewjohnclose wrote: Hi, I have been trying to create a function to generate a Procrustes plot, generated from package vegan in lattice. standard vegan code as follows library(vegan) pro=protest(P1, P8, permutations=4999,choices=1:4) plot(pro) Now, here is the code for the function that I have failed to get to work properly. panel.procrustes=function(x,y) }Pro=protest(x,y,permutations=4999,choices=1:4) Proplot=plot(Pro) } xyplot(P1[1:4]~P8[1:4],panel=panel.procrustes) I can generate an empty plot, but not much else - hope someone can help and point out the obvious! Kind regards Andrew The obvious thing is that whole thing is wrong! ;-) What's wrong with the standard plot? You are trying to mix base (standard) graphics functions with grid/lattice graphics and this is not possible (well Ok there is package gridBase). You'll have to start doing the plotting from scratch in panel.procrustes. You might get some ideas of how to do this by looking at the ordixyplot functions and panel functions in current vegan that implement lattice graphics plots for ordiplot objects. I'm not sufficiently familiar with Lattice yet to advise how to go about producing a panel function, but the basic elements are: * draw the points from x$Yrot[, 1:2] * draw the arrows from x$Yrot[, 1:2] to x$X[, 1:2] * draw the origin - equivalent of abline(h = 0) and abline(v = 0) * draw the rotation involved in the Procrustes analysis: abline(0, tan(acos(x$rotation[1, 1])) and abline(0, 1/tan(acos(-x $rotation[1, 1])) So you'll need the Lattice equivalents of abline and then work out how to pass the X, Yrot and rotation components to your panel function. This is the bit I'm not clear on but look at ordixyplot and panel.ordi for inspiration. Here is a relatively simple demonstration of creating a custom panel function: http://casoilresource.lawr.ucdavis.edu/drupal/node/630 Cheers, Dylan -- Dylan Beaudette Soil Resource Laboratory http://casoilresource.lawr.ucdavis.edu/ University of California at Davis 530.754.7341 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Mixed effects model where nested factor is not the repeated across treatments lme???
Hi Miki and Chunhao, Rusers (Anna, and Mark {thank you guys}) provide me a vary valuable information. Also see Gavin Simpson's posting earlier today: apparently multcomp does now work with lmer objects (it's gone through phases of not working, then working: it's still being developed). Beware, though, that random effects are specified differently, so it's not as easy to recast an aov(... + Error(...)) term structure as an equivalent random effect's structure. HTH, Mark. ctu wrote: Hi Miki, I just got the same problem with you couple hours ago. Rusers (Anna, and Mark {thank you guys}) provide me a vary valuable information. link to following address. http://www.nabble.com/Tukey-HSD-(or-other-post-hoc-tests)-following-repeated-measures-ANOVA-td17508294.html#a17559307 for the A vs. B, A vs. C You could install and download the multcomp package and perform the post hoc test such as summary(glht(lmel,linfct=mcp(treatment=Tukey))) hopefully it helps Chunhao Quoting M Ensbey [EMAIL PROTECTED]: Hi, I have searched the archives and can't quite confirm the answer to this. I appreciate your time... I have 4 treatments (fixed) and I would like to know if there is a significant difference in metal volume (metal) between the treatments. The experiment has 5 blocks (random) in each treatment and no block is repeated across treatments. Within each plot there are varying numbers of replicates (random) (some plots have 4 individuals in them some have 14 and a range in between). NOTE the plots in one treatment are not replicated in the others. So I end up with a data.frame with 4 treatments repeated down one column (treatment=A, B, C, D), 20 plots repeated down the next (block= 1 to 20) and records for metal volume (metal- 124 of these) I have made treatment and block a factor. But haven't grouped them (do I need to and how if so) The main question is in 3 parts: 1. is this the correct formula to use for this situation: lme1-lme(metal~treatment,data=data,random=~1|block) (or is lme even the right thing to use here?) I get: summary(lme1) Linear mixed-effects model fit by REML Data: data AIC BIClogLik 365.8327 382.5576 -176.9163 Random effects: Formula: ~1 | block (Intercept) Residual StdDev: 0.4306096 0.9450976 Fixed effects: Cu ~ Treatment Value Std.Error DF t-value p-value (Intercept) 5.587839 0.2632831 104 21.223688 0. *** TreatmentB -0.970384 0.3729675 16 -2.601792 0.0193 *** TreatmentC -1.449250 0.3656351 16 -3.963651 0.0011 *** TreatmentD -1.319564 0.3633837 16 -3.631323 0.0022 *** Correlation: (Intr) TrtmAN TrtmCH TreatmentB -0.706 TreatmentC -0.720 0.508 TreatmentD -0.725 0.511 0.522 Standardized Within-Group Residuals: Min Q1 Med Q3 Max -2.85762206 -0.68568460 -0.09004478 0.56237152 3.20650288 Number of Observations: 124 Number of Groups: 20 2. if so how can I get p values for comparisons between every group... ie is A different from B, is A different from C, is A different from D, is B different from C, is B different from D etc... is there a way to get all of these instead of just is A different from B, is A different from C, is A different from D which summary seems to give? 3. last of all what is the best way to print out all the residuals for lme... I can get qqplot(lme1) is there a pre-programmed call for multiple diagnostic plots like in some other functions... Thankyou so Much for your time It is much appreciated ;-) Miki [[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. -- View this message in context: http://www.nabble.com/Mixed-effects-model-where-nested-factor-is-not-the-repeated-across-treatments-lmetp18732327p18738202.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] bug in 'margins' behavior in reshape - cast
I want the column that is never going to actually have the '(all)' level to not become of type factor. continuing the example: chick_m$diet = as.integer(as.character(chick_m$diet)) is.factor(chick_m$diet) #returns FALSE is.factor(cast(subset(chick_m, time == 0), diet + chick ~ time, mean, margins=diet)$diet) #returns TRUE does that make sense? the way it works now, it totally screws things up when the column for which you get margins is not a factor. in my case, a date column. thanks, Mike hadley wrote: On Wed, Jul 30, 2008 at 11:47 AM, mfrumin [EMAIL PROTECTED] wrote: according to the documentation of the cast function in the reshape function, I would expect this bit of code from the examples to calculate marginal means over only the 'diet' variable. #Chick weight example names(ChickWeight) - tolower(names(ChickWeight)) chick_m - melt(ChickWeight, id=2:4, na.rm=TRUE) cast(chick_m, diet + chick ~ time, mean, margins=diet) But, summary(cast(subset(chick_m, time == 0), diet + chick ~ time, mean, margins=diet)) returns: dietchick 0 1:21 (all) : 4 Min. :39.00 2:11 18 : 1 1st Qu.:40.85 3:11 16 : 1 Median :41.00 4:11 15 : 1 Mean :41.05 (all): 0 13 : 1 3rd Qu.:42.00 9 : 1 Max. :43.00 (Other):45 which shows that it calculated margins on the 'chick' column as well. this behavior causes great problems for me when in my data one of the columns is a non-factor column, eg a Date, but the unrequested margining behavior turns that column into a factor. am I missing something? Hi Mike, I'm not sure what you want - if you want margins at the diet level, then you have to margin over all of the chicks at that level, which is then displayed as (all). Maybe you want margin = grand_row ? Hadley -- http://had.co.nz/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/bug-in-%27margins%27-behavior-in-reshape---cast-tp18737649p18738699.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] best quad core configuration?
Le mer. 30 juil. à 13:04, Alan Swanson a écrit : I am purchasing a quad-core 64-bit system. My proposed configuration is an intel core duo quad with 8Gb memory and an ubuntu OS. I'm choosing ubunto because I have good local support, but it doesn't seem as well supported as debian for R. And what makes you think that? First off, Ubuntu is Debian based, so every Debian package (well, the R ones at least) is also in Ubuntu. Second, we also provide backports of R for Ubuntu releases down to Dapper. I consider this is rather good support; see http://cran.r-project.org/bin/linux/ubuntu/ Will ubuntu limit me in any significant way? I have noticed a bias towards AMD machines among R users - are there compelling reasons to go with an equivalent AMD system instead? Will I be able to use amd64 binaries on this system, or would I have to compile everything myself? As the README file linked above mentions, we provide up-to-date R binaries for i386 and amd64. For your other points, I will let more competent people answer. --- Vincent Goulet, Associate Professor École d'actuariat Université Laval, Québec [EMAIL PROTECTED] http://vgoulet.act.ulaval.ca Would it difficult to install Intel MKL 10.0 BLAS and LAPACK libraries on this machine? Would it be difficult to run both 32-bit and 64-bit versions of R on this machine? The most computationally-intensive thing I will be using the machine for is large MCMC simulations, probably using multiple instances of LinBUGS. Any advice on configuring by machine for maximum speed for these simulations? Thanks, Alan Swanson [[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] About clustering techniques
Hi Christian I've been reading about daisy and think I need to do something like.. mydaisydata - daisy(mydata,metric=c(euclidean),stand=FALSE) Error en vector(double, length) : tamaño del vector especificado es muy grande(which means, specified vector size is too big) mydata is an anual file with 14 columns by 124716 rows. Is it possible that daisy can't handle this data? maybe I'm missing something when using daisy. Another question, if I get daisy running I can use kmeans like this? mykmeansdata - kmeans(mydaisydata, 5) or pamk that I've read it gives the optimal number of clusters. Thanks again -- _ El ponent la mou, el llevant la plou Usuari Linux registrat: 363952 --- Fotos: http://picasaweb.google.es/pacomet [[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] setting editor environment variable EDITOR either when configuring R for installation or in .Rprofile
on 07/30/2008 12:54 PM Mark Kimpel wrote: I'm running R on Linux and use emacs as my editor. When doing edit(vignette(foo.vignette)) I would like to invoke emacs rather than the default vi. I am able to manually set this by editing $R_HOME/etc/Renviron but would like to avoid doing this with each install. I assume this can be accomplished with a flag to .configure or in .Rprofile but I can't find the syntax in R-admin. Editor is not listed as an environment variable in appendix B of that manual. So, help is appreciated as I've probably missed something. Mark Mark, See ?options for 'editor'. This is also referenced in ?edit, where the default value for the 'editor' argument is getOption(editor). Thus, in your .Rprofile, put: options(editor=emacs) HTH, Marc Schwartz __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Random subset
Hi all, I wish to do a random subset (i.e. 200 or 300 points) from a dataset, but I don't find the right code in R. Thanks for help alessandro [[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] john chambers R book
Just to let everyone know: John Chambers R book is no longer at pre-order status on Amazon which is a good thing. The only problem is that now it is temporarily out of stock. There must have been many pre-orders so now I'm kicking myself for not having done that. Mark __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Random subset
?sample --- On Wed, 7/30/08, Alessandro [EMAIL PROTECTED] wrote: From: Alessandro [EMAIL PROTECTED] Subject: [R] Random subset To: r-help@r-project.org Received: Wednesday, July 30, 2008, 2:18 PM Hi all, I wish to do a random subset (i.e. 200 or 300 points) from a dataset, but I don't find the right code in R. Thanks for help alessandro [[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. __ [[elided Yahoo spam]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Re gression between columns in matrix - with some/full NAs
Hi Anna, Thanks for your reply and suggestions. I'm trying something different, based on regression this time, albeit giving similar problems. I want to regress a single column in a matrix with each other column in the same matrix, and o/p the intercept and slope coefficients to a results matrix. The loop below works, even when I have columns with partial NAs, but exits with an error when a column with only NAs is encountered. So, the 'na.action=NULL' statement (see last line of code below) doesn't seem to work in this case, or perhaps I am applying it incorrectly. I would be very grateful for any pointers in the right direction: tt-time(SourceMat) ResultMat-matrix(NA, ncol=colnum, nrow=rownum) #creates an o/p template matrix #loop through each column in the source matrix: for (i in 1:5000) { sel_col-[col(SourceMat)==i]#selecting the correct column in the matrix in turn SourceMat[,i]-coef(lm(tt~sel_col), na.action=NULL) } Thanks, rcoder rcoder wrote: Hi everyone, I'm having trouble applying the Cor() function to two matrices, both of which contain NAs. I am doing the following: a-cor(m1, m2, use=complete.obs) ... and I get the following error message: Error in cor(m1, m2, use = complete.obs) : no complete element pairs Does anyone know how I can apply a correlation, ignoring any NAs? Thanks, rcoder -- View this message in context: http://www.nabble.com/correlation-between-matrices---both-with-some-NAs-tp18721853p18739148.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] Random subset
Hi, check ?sample n - 200 mydata.set - rnorm(10) my.random.subset - sample(x=mydata.set, size=n, replace=TRUE) my.random.subset I hope this helps, Roland Alessandro wrote: Hi all, I wish to do a random subset (i.e. 200 or 300 points) from a dataset, but I don't find the right code in R. Thanks for help alessandro [[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.
[R] History pruning
Hi, I find that a typical workflow for me looks something like this: 1) import some data from files 2) mess around with the data for a while 3) mess around with plotting for a while 4) get a plot or analysis that looks good 5) go back through my history to make a list of the shortest command sequence to recreate the plot or analysis 6) send out that sequence to colleagues, along with the generated plots or analysis output I wonder if there are any tools people have developed to help with step 5. Typically I do something like this: 5a) save my entire history to a text file 5b) open it up in Emacs 5c) prune any lines that don't have assignment operators 5d) prune any plotting commands that were superseded by later plots and then start on other more subtle stuff like pruning assignments that were later overwritten, unless the later assignments have variable overlap between the LHS and the RHS. Then I just start eyeballing it. Would any deeper introspection of the history expressions be feasible, e.g. detecting statements that have no side effects, dead ends, etc. The holy grail would be something like show me all the statements that contributed to the current plot or the like. Thanks. -- Ken Williams Research Scientist The Thomson Reuters Corporation Eagan, MN __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] Variable name in a String
Hi all, I have this string year and integer 2008 (both are inputs from the user), and I would like to make a variable called year2008 that will store a vector of numbers. Does anyone know how to do this? Also, if the user later input year and 2008, how do I treat this as a variable; how can I access the variable year2008 using the string paste(year,2008,sep=)? Thanks so much! -- View this message in context: http://www.nabble.com/Variable-name-in-a-String-tp18738356p18738356.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] rolling regression between adjacent columns
Well, in this case I don't think my original code would have helped much... So, I've rewritten as below. I want to perform regression between one column in a matrix and all other columns in the same matrix. I have a for loop to achieve this, which succeeds in exporting intercept and slope coefficients to a results matrix, except when a column that contains only NAs is reached. Columns partially filled with NAs are handled, but the code exits with errors when a single column is filled with NAs. I inserted the 'na.action=NULL' statement within the lm() construct, but to no avail. I would be very grateful for any advice. tt-time(SourceMat) ResultMat-matrix(NA, ncol=colnum, nrow=rownum) #creates an o/p template matrix #loop through each column in the source matrix: for (i in 1:5000) { sel_col-[col(SourceMat)==i] #selecting the correct column in the matrix in turn SourceMat[,i]-coef(lm(tt~sel_col), na.action=NULL) } Thanks, rcoder Gabor Grothendieck wrote: Read the last line of every message to r-help. On Tue, Jul 29, 2008 at 6:15 PM, rcoder [EMAIL PROTECTED] wrote: Hi everyone, I am trying to apply linear regression to adjacent columns in a matrix (i.e. col1~col2; col3~col4; etc.). The columns in my matrix come with identifiers at the top of each column, but when I try to use these identifiers to reference the columns in the regression function using rollapply(), the columns are not recognised and the regression breaks down. Is there a more robust way to reference the columns I need, so that I can apply the regression across the matrix; 'by.column', but every other column? Thanks, rcoder -- View this message in context: http://www.nabble.com/rolling-regression-between-adjacent-columns-tp18722392p18722392.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/rolling-regression-between-adjacent-columns-tp18722392p18739292.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] Random subset
But probably you will need to set replace=FALSE if you want to sample from your original data set without replacement. Sorry for the possible confusion, Roland Roland Rau wrote: Hi, check ?sample n - 200 mydata.set - rnorm(10) my.random.subset - sample(x=mydata.set, size=n, replace=TRUE) my.random.subset I hope this helps, Roland Alessandro wrote: Hi all, I wish to do a random subset (i.e. 200 or 300 points) from a dataset, but I don't find the right code in R. Thanks for help alessandro [[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. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/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] System exit codes
Hi -- Is there a way of detecting the exit code while calling system or pipe? eg (on Unix) system(perl -e 'print \foo\\\n\;exit(-1);') foo Any help appreciated, Ranjan __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.