similar to: save.image() issue resolved - I hope

A week or so ago, I reported a problem on my new Windows XP box getting R 1.4.1 and R 1.5.0 (development from BDR's site) to save the .RData file upon program exit. Specifically, either clicking on the "X" in the GUI or invoking q() from the command line produced the following error: Error in save.image(name) : image could not be renamed and is left in .RDataTmp1 After some

I have an environment consisting of: * Primary Workstation running Win2KPro * Secondary Workstation runing WinNTSP6a * Local Win2K Advanced Server * Local Solaris 8 system with Samba 2.0.7 * Remote HP-UX system at Site A with Samba 1.9.18p10 connected via VPN * Remote Unixware system at Site B with Vison(?) file sharing connected via VPN * Three remote Win2K server boxes at Site C connected via

Hello, Does logistic regression really provide better results than lda or qda ? (my purpose is not classification but highlighting of discriminant variables). If this is true, where could I get an R script performing stepwise logistic regression ? Thanks -- Daniel AMORESE Lab. M2C "Morphodynamique Continentale et C?ti?re" UMR CNRS 6143 Caen/Rouen Centre de G?omorphologie UCBN

Are there any S-Plus or R libraries/packages that do Finite Mixture Analysis following the algorithms similar to those implemented in Geoffrey MacLachlan's EMMIX program? Thanks. Dr. Marc R. Feldesman email: feldesmanm at pdx.edu email: feldesman at attglobal.net fax: 503-725-3905 "Don't know where I'm going. Don't like where I've been. There may be no exit. But

I ran across this error the other day while using lm(). I confess that I haven't used it for awhile and haven't been tracking the changes between versions of R. However, the piece of code below is a tiny modification of the example in the help file for "lm". I just separated the commands apart for clarity. A similar piece comes from the help file for

I have in my inbox a note saying books are expected in early August. However, for R users there is relatively little advantage in the third edition, except that almost everything works unchanged. The real advantages of the third edition are for users of S-PLUS 5.x and 4.5/2000. > From: Marc R. Feldesman > To: guido at hal.stat.unipd.it; 'Guido Masarotto '; 'Maria Wolters '

What is the generally accepted way to put certain math symbols into plain text email? For example, how does one convey the "is exactly equal to", "is approximately equal to", and "delta" symbols in a standard text-based (e.g. Courier) font? Dr. Marc R. Feldesman email: feldesmanm at pdx.edu email: feldesman at attglobal.net fax: 503-725-3905

Hi there. I'm running Samba 2.2.3a on RedHat 7.1 + kernel 2.4.17. My girlfriend's laptop is running Windows 2000 + service pack 2. She has about a thousand MP3s stored on a Samba share on my RedHat machine. We were finding that she couldn't rename any MP3s on the Samba share: she would always get a sharing violation. After a day of reading Samba logs at debug 10 (_such_ fun [ ;)

I just updated rpart to the latest version (3.1.0). There are a number of changes between this and previous versions, and some of the code I've been using with earlier versions (e.g. 3.0.2) no longer work. Here is a simple illustration of a problem I'm having with xpred.rpart. iris.test.rpart<-rpart(iris$Species~., data=iris[,1:4], parms=list(prior=c(0.5,0.25, 0.25))) + ) >

Probably wrong group for this, but a quick question. I've just switched from emacs to Xemacs. In reinstalling ESS 5.1.19 I keep getting the following error when loading Xemacs: "Error in init file: Symbol's function definition is void: w32-using-nt" I've debugged the ess-site.el file, which is where the error originates from. The line causing the difficulty is:

Is there any effective way to get distinct geometric plotting symbols and colors for plots involving more than 25 groups? Thanks. Dr. Marc R. Feldesman Professor and Chairman Emeritus Anthropology Department - Portland State University email: feldesmanm at pdx.edu email: feldesman at attglobal.net fax: 503-725-3905 "Don't knock on my door if you don't know my

Sorry for the off-topic post, but there is such a wealth of knowledge here that I thought someone might have suggestions. Geoff MacLachlan and David Peel have a program - EMMIX - available for mixture modelling. It is only available as FORTRAN source code and is "downloadable" from Geoff's site. The code is reputed to run on Unix machines and is compilable according to

In my research area, researchers are very stingy about sharing data. In fact, they are frequently downright secretive about these morsels. Typically, we get fed a diet of summary statistics and the assurance that the data are *normal* without any necessary documentation that they really are. With that as background and assuming that the data really are normal, is there any way in R (or any

I have a Samba Domain that did migration from: 3.0.0 -> 3.0.2 -> 3.0.2a ->3.0.4 It is a very healthy machine it is running on. A heavily updated RedHat 7.2 machine. I have rebuilt newer source SRPM to update it. Pretty much updated piece meal since forever, and probably is updated e"enough". It is lean, as I do not believe in Garbage installs. But, the point of this is:

Thanks to all who offered advice on how to solve a loss of resolution problem involving ps from R, ps -> eps from Acrobat, and Word. It appears that this problem will need to be resolved inside R. If I try to add anything additional (more text, clipart embellishments) to a ps/eps file (using, say, Adobe Acrobat, PaintShop Pro, Powerpoint, or Adobe Illustrator), it gets placed as a

I'm running R 1.5.1 under Windows XP Pro. I haven't paid too much attention to the way R starts up until now. I've noticed that on all my Windows XP systems, Rgui.exe starts "maximized" despite having the shortcut properties set for it to run in a "normal" window. I've tried resizing the windows (I use MDI sessions) and then saving the workspace, but the

Just a quick followup to the query I posted yesterday. The default screen layout for the Windows version of R (1.5.1 currently) is MDI, which has the RGUI itself maximized over the entire screen, while the R console is in a smaller window inside the RGui. I asked whether there was some way at startup to change the amount of screen real-estate occupied by the RGui itself since this can be

Congratulations to Bill Venables and Brian Ripley for their latest "tour de force" - MASS 4, which just arrived in my mailbox last week. As always, the book contains new pearls of wisdom to improve my statistical and programming skills. Kudos also to Peter Dalgaard for his "Introduction to Statistics with R". It is a delightful volume that I can recommend to all those

Thanks to John Day, Tom Richards, Mike Prager, Thomas Lumley, and Goran Brostrom, for various helpful suggestions that finally allowed me to get EMMIX compiled on my Linux (and my Windows) machines. The problem was a simple case-sensitivity issue concerning a single file, which I had correctly downloaded but named using the wrong case ("emmix.max" instead of "EMMIX.max").

I've created a bunch of postscript trees (post.rpart), which I subsequently edit in Adobe Acrobat 4.05 (I need additional labelling that isn't easy to add with R). After editing the labels and annotations using Acrobat, I then export the file to Adobe's .eps format so I can insert the picture into a Microsoft Word 2000 document. The .pdf file distilled from the .ps file is