Re: [R] questions about principle component analysis (princomp)

Yunfeng Hu wrote: Hi, I am a new R user and am currently using princomp to conduct a PCA. I have read the help(princomp) and still do not quite understand everything in the help. Basically I want to get the covariance matrix, and eigenvector/eigenvalues (loadings()?) so that I can find the

Re: [R] dumpClass, hasSlot in R?

Marc Schwartz MSchwartz at MedAnalytics.com writes: : : On Wed, 2004-07-21 at 15:53, hadley wickham wrote: : There are a few notes about difference between the R implementation : and the book at http://developer.r-project.org/methodsPackage.html : : I found the hardest thing to get to grips

Re: [R] add more data to a data file, problem with .Rprofile

Liaw, Andy wrote: From: Francisco J Molina Hi, Is there a way to incorporate an R object x to a file already containing R objects? It seems that 'save' is not capable to do this. If I save x to a file containing previously saved data, then I will lose this data. See if the following helps: x -

[R] Programmation pour MLE

Salut, je pense tu dois calculer/determiner la function of vraisemblance di f(x). D'après tu peux chercher le valeur des parametres a1,a2,a3 che rendent maxime la vraisemblance di f(x) en employant les funtions de R: optimize() or optim() pur maximizer la vraisemblance di f(x) avec des methodes

[R] Population Pyramid Plot

Finally, today I able to produce pyramid plot using any part of script from R-News Vol 3/2, October 2003 by Paul Murrell Integrating grid Graphics output with Base Graphics Output. Title, i using title function from script in http://www.r-project.org/misc/acpclust.R . Maybe, anyone to improve

[R] Vector to complex scalar

Is there an R function to convert vectors into complex scalars? Thanks Laura Quinn Institute of Atmospheric Science School of the Environment University of Leeds Leeds LS2 9JT tel: +44 113 343 1596 fax: +44 113 343 6716 mail: [EMAIL PROTECTED] __

Re: [R] Vector to complex scalar

Laura Quinn wrote: Is there an R function to convert vectors into complex scalars? Thanks Is this because of the wind problem in one of the last questions? For conversion of two dimensional data into complex numbers and vice-versa you may look for ?complex in the online help, however I do not know

[R] Disriminant analysis with lda (MASS)

Hello, Does the lda function (package MASS) perform or can it perform classic two-group Fisher discriminant analysis? R-version: 1.9.1, MASS package (latest available) Thank you, Borut Rajer __ [EMAIL PROTECTED] mailing list

Re: [R] Building problem: leftover from old OS

I guess that you built R before (in the same location for Solaris 2.7) ? If yes, make clean (or just wipe out everything, and unpack the R-1.9.1.tar.gz again) before calling configure should solve the problem. BTW: I'd recommend to build in a different directory than the source one.

[R] exporting high quality graphics from R in Mac OSX

Hi there The default option for saving graphics from R (1.9.1) on my Mac is as a pdf file. If I open the file in Acrobat reader it looks really good and crisp, and is obviously saved as vector graphics, since I can zoom in as much as I like and it continues to look really nice. If I import it

Re: [R] Disriminant analysis with lda (MASS)

If memory serves, Fisher's Discriminant analysis produces the same results as lda for two groups although the assumption and derivations are different. Google search produces http://www.statsoftinc.com/textbook/stdiscan.html In the middle of page 347 of MASS 3 (sorry no latest copy here), it

Re: [R] add more data to a data file, problem with .Rprofile

You should take a look at ?setHook if you use hsv() in .Rprofile. That way when the `graphics' package is loaded, it will automatically run whatever hook function you specified involving hsv(). For example, you might include something like setHook(packageEvent(graphics, onLoad),

Re: [R] exporting high quality graphics from R in Mac OSX

R's PDF is indeed vector graphics. Given that PDF is supposedly the native graphics representation on MacOS X, it sounds as if you are not using MacOS X native applications (and Office 2000 cannot be, given its date). If you are indeed using classic MacOS applications then the native graphics

Re: [R] exporting high quality graphics from R in Mac OSX

Nope, sorry, I made a mistake - it's Office vX, native for OSX. I've had a look around and found quite a few complaints on the 'net about Word X claiming to be OSX native but rendering the image as a scruffy bitmap, so I guess this is a Word problem. I don't want to invest in the newest

RE: [R] RE: Comparison of correlation coefficients - Details

Dear Ioannis Thank you very much for pointing me to meta-analysis. Although it may not solve my problem with the normalization, it gives me some other options to display the different correlation coefficients. One possibility is the use of Funnel plots, which are even available in

Re: [R] exporting high quality graphics from R in Mac OSX

On Thu, 22 Jul 2004 14:03:23 +0100, Rob Knell [EMAIL PROTECTED] wrote : Nope, sorry, I made a mistake - it's Office vX, native for OSX. I've had a look around and found quite a few complaints on the 'net about Word X claiming to be OSX native but rendering the image as a scruffy bitmap, so I

Re: [R] Precision in R

On 22 2004, at 06:09, [EMAIL PROTECTED] wrote: Message: 5 Date: Wed, 21 Jul 2004 13:48:53 +0200 From: [EMAIL PROTECTED] ( Bj?rn-Helge Mevik ) Subject: Re: [R] Precision in R To: [EMAIL PROTECTED] Message-ID: [EMAIL PROTECTED] Content-Type: text/plain; charset=iso-8859-1 Since you didn't say

Re: [R] Programmation pour MLE

On Thu, Jul 22, 2004 at 06:48:58AM +0200, Ahmed Elhabti wrote: Je veux cherch? l?estimateur de vraisemblance maximal (MLE)d?une fonction ? 3 param?tre inconue ?tant donn? une ?chantillon de taille 50 (les observations des valeurs de x) alors comment je peux proc?d? La fonction de densit?

[R] gcc on AIX is not compatile with R-1.9.1

Hi Uwe Liqqes, Does the successful compilation for R-1.9.1 on AIX 5.1 depend on the IBM AIX compiler for C and C++ (xlc/xlC)? gcc on AIX is not compatible with R1.9.1. Kexiao -Original Message- From: Uwe Ligges [mailto:[EMAIL PROTECTED] Sent: Sunday, July 18, 2004 8:19 AM To: Liao,

[R] Problem with listbox

Hi! I'm using two listboxes for some selection. When I select an entry in one listbox than the selection in the other listbox disappears. How can I keep the selection visible in the listbox which lost the focus? Thanks! Torsten __ [EMAIL PROTECTED]

[R] package nls2 for windows

Dear Madam or sir, Does anyone know if there is a pre-compiled version of package nls2 for windows, please? Thank you. Souleymane __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the

Re: [R] package nls2 for windows

Have you tried Google? The first two entries for `nls2 Windows' explain this for you. I suspect very few readers of R-help even know what `nls2' is -- it is not a package on CRAN , not in any other repository mentioned in the FAQ. I am guessing you mean the one Google throws up. On Thu, 22

Re: [R] exporting high quality graphics from R in Mac OSX

Hi! There is one more option that you may try: dev.copy2eps(file=file_name.eps) Good look. On Thu, 22 Jul 2004, Rob Knell wrote: Nope, sorry, I made a mistake - it's Office vX, native for OSX. I've had a look around and found quite a few complaints on the 'net about Word X claiming to be

[R] Replace only Capital Letters

Dear All, I have these data: exampledata - c(This is one item, This is Another One, And so is This) I would like to find each occurence of a blank space followed by a Capital Letter and replace it by a blank space, a left curly brace, the respective Capital Letter, and then a right curly brace.

Re: [R] Replace only Capital Letters

This appears to be a bug. Please try gsub(pattern = ([A-Z]), replacement = {\\1}, x=exampledata, perl=TRUE) On Thu, 22 Jul 2004, Rau, Roland wrote: Dear All, I have these data: exampledata - c(This is one item, This is Another One, And so is This) I would like to find each

Re: [R] questions about principle component analysis (princomp)

Thank you, Thomas. It is very helpful. I will dig more into the man page but for now I get what I want. Yunfeng On Jul 21, 2004, at 11:29 PM, Thomas Petzoldt wrote: Yunfeng Hu wrote: Hi, I am a new R user and am currently using princomp to conduct a PCA. I have read the help(princomp) and still

Re: [R] Replace only Capital Letters

Another solution (that is correct in other locales than C, since I see you are not in an English locale). gsub(pattern = ([[:upper:]]), replacement = {\\1}, x=exampledata) I think this _is_ the problem, as in your locale (and in en_GB) the sort order is probably something like aAbB...zZ Or

[R] sorting Trellis panels

Can anyone explain how to properly use index.cond? I cannot include it in the xyplot command and get what I expect. For example, plot-xyplot(y ~ x | z, data) # let's say z is a factor with six levels gives a nice plot but I am unhappy with the order of panels. I can get the order I

[R] biplot identify

Hi! Is there a way to get biplot and identify to work togheter. Having the output of prcomp I would like to draw a biplot that. Instead of plotting the sample (row-names) names plots some pch symbols. (thats easy with xlabs) But now I would like to add using identify the names to only some of

Re: [R] sorting Trellis panels

Quoting Patrick Lorch [EMAIL PROTECTED]: Can anyone explain how to properly use index.cond? I cannot include it in the xyplot command and get what I expect. For example, plot-xyplot(y ~ x | z, data) # let's say z is a factor with six levels gives a nice plot but I am unhappy

[R] compile error on aix 5.2 using gcc 2.9-aix51-020209

Dear R Development Team, I just compile R-1.9.1 on AIX 5.2 using gcc 2.9-aix51-020209. During the compile process, there is an error message saying return type mismatch in R_HOME/src/modules/X11/devX11.c line 1768. Following is the part of the C codes from file devX11.c /** This

[R] Precision in R--SOLVED!

Greetings. I'd like to thank everyone who sent me suggestions of what might have been wrong, especially Matt Austin. He did not actually give me the solution, but rather he inadvertently set me on the path to find it by effectively getting me to look closer at the code I was using. And thus

Re: [R] exporting high quality graphics from R in Mac OSX - solution

Thanks to everyone for all the suggestions. Turns out this is purely a Word problem, so the solution is to use the word processor in Apple Works, which will happily import lovely crisp vectors from a pdf, do 99% of the things you might want MS Word to do, and won't try to annoyingly pre-empt

[R] Files and classes in a package?

While installing my small package, I met a tricky problem. For clarity, let me explain it with the following simplified example. In ~/pkg/R/aclass.R, setClass(“aclass”, contains=”bclass”, representation(i=”numeric”)) In ~/pkg/R/bclass.R, setClass(“bclass”, representation(j=”numeric”))

Re: [R] Files and classes in a package?

Please do read the documentation, in this case the `Writing R Extensions Manual. The para starting An optional @samp{Collate} field (or OS-specific variants @[EMAIL PROTECTED], such as e.g.@: @samp{Collate.windows}) can be used for controlling the collation order for the R code files in a

[R] Standard error of a sum

Folks, This is so simple is driving me crazy. It's not really an R question is more an Statistics question. I applied a chemical in 3 different events during a growing season. I took 3 samples in each event to estimate mean applied chemical. Thus, I can easily estimate means and st.err by

Re: [R] Standard error of a sum

The variance of a sum is the sum of all the elements of the variance-covariance matrix. If the summands are uncorrelated, then the variance of the sum is the sum of the variances. hope this helps. spencer graves Jose A. Hernandez wrote: Folks, This is so simple is driving me crazy. It's not

[R] viewing Postscript file

Is there any R function that can display a Postscript file that is already in the working directory? For example, if 'graph.ps' is such a file, I'd like to type something like this: plot.postscript.file(file = 'graph.ps') If no such function exists, I'd be interested in a way to use existing R

[R] help on R plot

Hi: I have a question about the R plot, I change the size of the y axis label from 1 to 2, but part of the word is missing as being cut. So I guess it is over the boudary of the R graphical setting. Would you please help me with it? How to change the boundary so that the full part of my

RE: [R] help on R plot

Dear Hang, Take a look at ?par, and in particular the graphical parameters mar and mai, which can be used to adjust the size of the margins of a plot. I hope that this helps. John -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Hang Lai Sent:

Re: [R] Standard error of a sum

If you supose that each mean is independent then s.err_total_chem - sqrt(sum(s.err_event^2)) If not you must estimate de var-covariance matrix to find this s.err. This estimation will be difficult given the scarce data available. Hope it will helps. Kenneth Jose A. Hernandez wrote: Folks, This is

Re: [R] help on R plot

I am not sure if I understand your question properly but try this par(mfrow=c(1,3)) plot(1:10, 1:10, xlab=A very long label here) plot(1:10, 1:10, xlab=A very long \n label here) plot(1:10, 1:10, xlab=A very long \n label here, cex.lab=2) Also have a look at help(par). On Thu, 2004-07-22 at

[R] Standard error of a sum

Was just looking at this data and tried this: event.var--tapply(d.1$chem,factor(d.1$event),var) event.var 1 2 3 -9.022233 -35.385033 -11.884433 Any idea why the variances are coming out negative. var(d.1$chem[1:3]) [1] 9.022233 right number Anyway here is

Re: [R] viewing Postscript file

On Thu, 2004-07-22 at 16:50, Bickel, David wrote: Is there any R function that can display a Postscript file that is already in the working directory? For example, if 'graph.ps' is such a file, I'd like to type something like this: plot.postscript.file(file = 'graph.ps') If no such

RE: [R] gcc on AIX is not compatile with R-1.9.1

From: Liao, Kexiao Hi Uwe Liqqes, Does the successful compilation for R-1.9.1 on AIX 5.1 depend on the IBM AIX compiler for C and C++ (xlc/xlC)? gcc on AIX is not compatible with R1.9.1. I believe GCC will work on AIX, but you most likely need a newer version than what you have. I

Re: [R] Standard error of a sum

Jim Brennan wrote: Was just looking at this data and tried this: event.var--tapply(d.1$chem,factor(d.1$event),var) event.var 1 2 3 -9.022233 -35.385033 -11.884433 Any idea why the variances are coming out negative. Yes, I think you meant: event.var -

[R] vetor autoregressions and BVARs

I have not been able to find any programs for running vector autoregressions with R. I am interested in running Bayesian VARs and also running VARs that run all combinations of variables in the vector. Is anyone currently developing this? -Nirav Mehta

Re: [R] vetor autoregressions and BVARs

A search - R site search from www.r-project.org for vector autoregression produced documentation of an mAr package for vector autoregression. Beyond this, a search for kalman filter time series produced 29 hits, most of which looked to me to be potentially relevant. Have you looked at

Re: [R] dumpClass, hasSlot in R?

Thanks to Hadley Wickham, Mar Schwartz, and Gabor Grothendieck. I'm skimming all 5 documents cited, and I will study them more later. Thanks again. Best Wishes, Spencer Graves Gabor Grothendieck wrote: Marc Schwartz MSchwartz at MedAnalytics.com writes: : : On Wed, 2004-07-21

[R] Modeling Dependent Bernoulli Trials?

Is there any software to estimate dependence between Bernoulli trials? I have N observations on k-vectors of 0s and 1s, and I need to model the dependence. Consider the simple case with k = 2. There are 4 possible outcomes: (0, 0), (0, 1), (1, 0), and (1, 1). I assume 0 =

[R] RE:Can R work on very large of data?

Hello, I guess it depends on what you call large and what you want to do and the memory. I've used R on 25,000 cases of 50 variables (mostly factor levels) for exploratory frequencies and plotting and found it fast (On a T23 IBM Thinkpad 512MB 1GHz proc). Regards Nigel