similar to: R-alpha: var() and missing

Is there an R function for computing a variance-covariance matrix that guarantees that it will have no negative eigenvalues? In my case, there is a *lot* of missing data, especially for a subset of variables. I think my tactic will be to compute cor(x, use="pairwise.complete.obs") and then pre- and post-multiply by a diagonal matrix of standard deviations that were computed based

Ok, I did the following experiment dyn.load("/usr/local/lib/libf2c.so.2.0") dyn.load("try.so") .Fortran("try", 10.5) where try.so contains the following compiled subroutine subroutine try(x) double precision x write(*,*) x return end It worked just fine (at least here on my FreeBSD machine at home). So it seems that it will be

The newest version of R for Unix (version R-0.50-a4) is now (or will soon be) available from the following sites. NORTH AMERICA: http://lib.stat.cmu.edu/R/Alpha EUROPE: ftp://ftp.stat.math.ethz.ch/R/ ftp://statlab.uni-heidelberg.de/pub/mirrors/auckland/R/ JAPAN: ftp://ftp.u-aizu.ac.jp/pub/lang/R/ NEW ZEALAND: ftp://stat.auckland.ac.nz/pub/R/

The newest version of R for Unix (version 0.50 alpha-1) is now (or will soon be) available from the following sites. NORTH AMERICA: http://lib.stat.cmu.edu/R/Alpha EUROPE: ftp://ftp.stat.math.ethz.ch/R/ ftp://statlab.uni-heidelberg.de/pub/mirrors/auckland/R/ JAPAN: ftp://ftp.u-aizu.ac.jp/pub/lang/R/ NEW ZEALAND: ftp://stat.auckland.ac.nz/pub/R/

This patch corrects the broken postscript graphics driver. If you have already done it by hand ignore this. Apply this patch within the R-0.49 directory. The patch is also at the auckland.ftp site and soon at mirrors. Ross *** src/unix/PostScript.c.orig Thu Apr 24 21:28:27 1997 --- src/unix//PostScript.c Thu Apr 24 21:28:51 1997 *************** *** 160,166 **** if(!MatchKey(buf, "C

A set of patches for R-0.50-a1 is now available as ftp://stat.auckland.ac.nz/pub/R/R-0.50-a1.patch1.gz The patches mainly fix problems reported since R-0.50-a1 but some older problems are also fixed. Here is the list of changes. Ross o Many subsetting and mutation problems with the new "expression" type have now been fixed. o When ask=T is set in par() the user is instructed

Here is a proposal: At present when you specify a color with an integer it is taken as an index into a fixed table of 8 colors. 1=red, 2=green, 3=blue, 4=cyan, 5=magenta, 6=yellow, 7=white, 8=black [At least this is the intention, there may be bugs in the implementation]. Since I am looking at this anyway (to see if I can see the bug that Martin and Kurt have mentioned) I thought I might

This is propagated to R-devel in case anyone else has a comment on this : >>>>> "MM" == Martin Maechler <maechler@stat.math.ethz.ch> writes: MM> On Aug. 14, MM> "Ross" == Ross Ihaka <ihaka@stat.auckland.ac.nz> writes: Ross> Re the emacs stuff: MM> ... Ross> 2. Peter Dalgaard made the suggestion that we made R source

A cut and paste typo has crept in and is rendering all values returned for the hypergeometric distribution incorrect. The problem is in src/main/arithmetic.c in the function "math4". The lines PROTECT(sy = allocVector(REALSXP, n)); a = REAL(sa); b = REAL(sb); c = REAL(sc); d = REAL(sc); /* <-- change this line */ y = REAL(sy); should

The .Options vector had been introduced a while ago after my suggestion (see Ross's E-mail below). .Options$digits is used be default in several print methods (eg print.lm), however, deparse(.) e.g., uses options()$width, and not .Options$width. Another problem is that .Options is still not in the documentation (on-line help). Before one could add it there, we'd need ``the

Martin Your revisions to my S--R compatability code suggest that tempfile() is in R after 0.49. I don't find that to be the case. It requires code from Friedrich Leisch which still has to be added as of 0.50 alpha3. Paul _______ R : Copyright 1997, Robert Gentleman and Ross Ihaka Version 0.50 Alpha-3 (August 8, 1997) > exists("tempfile", mode = 'function') [1] FALSE >

>> ------------------------ >> R & R, any comments? >> ------------------------ At present the parser makes the decision on what characters can go into symbol names based on isalpha(c). If someone will send me a function - say isidchar(c) which returns 1 for characters which can be in identifiers and 0 otherwise, I will replace the current test with that. Ross

Attached is an updated version of the FAQ, to be released right after 0.50 is out. Please have a look, and let me know where improvements are needed. Thanks, -k ******************************************* R FAQ Kurt Hornik v0.1-0, 1997/04/16 This document contains answers to some of the most frequently asked questions about R. Feedback is welcome.

Jeez I dunno - it compiles perfectly and you guys get excited just because it doesn't work :-) I have to admit to being baffled about what happened (I'm SURE this was working not long ago), but here is a quick fix. The problem is in the function "GetCharInfo" in the file src/unix/PostScript.c. The fix is to change the statement if(nchar < 0) return 0; to if(nchar <

1) I have been working on making R libraries more like those in S. I thought it might be advisable to discuss the ideas before springing them on you. What I have done is changed things so that each library has its own frame on the search path. E.g. > search() [1] ".GlobalEnv" "library:base" > library("eda") > search() [1] ".GlobalEnv"

I must admit to being baffled by this. When I type "R" I get R : Copyright 1997, Robert Gentleman and Ross Ihaka Version 0.50 Beta (April 1, 1997) R is free software and comes with ABSOLUTELY NO WARRANTY. You are welcome to redistribute it under certain conditions. Type "license()" for details. > gc() Garbage collection ... 150427 cons cells free (75%) 1823k

Why does parse not work below and why does assigning it crash R? Paul ________ $ R R : Copyright 1997, Robert Gentleman and Ross Ihaka Version 0.50 Alpha-3 (August 8, 1997) R is free software and comes with ABSOLUTELY NO WARRANTY. You are welcome to redistribute it under certain conditions. Type "license()" for details. > system("date \'+%Y %m %d %H %M %S\'",

Dear help I have been attenpting to compile R0.49 on both of these unix machines and have had no compilation errors but core dumps at run time. The HP UX box start out by putting up a graphics window and then crashing with the following error message before giving the prompt R : Copyright 1997, Robert Gentleman and Ross Ihaka Version 0.49 Beta (April 23, 1997) R is free software and

Just a short reminder / question -- We've had one posting >> Date: Sun, 17 Aug 1997 19:51:20 -0700 >> From: Kung-Sik Chan <kchan@stat.uiowa.edu> >> To: r-help@stat.math.ethz.ch >> Subject: R-beta: bug report with a predict.default that would "work" with (some) lm objects, and I think it was said that predict.lm "is being" written (Peter

A second patch for R-0.50-a1 is available from ftp://stat.auckland.ac.nz/pub/R The patch produces the following changes o cpoly problem with pow_di fixed. o legend had a call to "text" with an incorrect argument tag. Changed "text" to "labels". o The variable "dup" was uninitialised in the function "naoktrim" in