search for: kjetilh

(I tried to send this earlier, but it doesnt seem to have come through, due to problems on my system) Hola: Both cannot be correct: > m <- matrix(1:4, 2) > svd(m) $d [1] 5.4649857 0.3659662 $u [,1] [,2] [1,] -0.5760484 -0.8174156 [2,] -0.8174156 0.5760484 $v [,1] [,2] [1,] -0.4045536 0.9145143 [2,] -0.9145143 -0.4045536 > La.svd(m) $d [1]

....in example data <- read.spss("c:/data.sav",use.value.label=F,to.data.frame=T) try help(read.spss) ! regards,christian kjetilh at umsanet.edu.bo schrieb am 28.08.02 02:08:39: > Hola! > > Can the foreign package now read data from spss 10? > > Kjetil Halvorsen > -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- > r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hor...

The following code in clusplot.default (package cluster) is in error: x1 <- cmdscale(x, k = 2, eig = TRUE) var.dec <- sum(x1$eig)/sum(diag(x1$x)) if (var.dec < 0) var.dec <- 0 if (var.dec > 1) var.dec <- 1 x1 <- x1$points x1 has components with names "points" and "eig", not "x", so

When R prints warnings, they often go "out of the line", it would be better if they where wrapped with writeLines(strwrap ... I tried to do that , changing the function warnings, but it has only effect when called explicitely, not when R prints the warnings unasked. Anyhow, here is the changed warnings: warnings <- function (...) { if (!(n <- length(last.warning)))

This morning I had 37 messages from the r-help list in my mailbox. I think its becoming excessive for an e-mail list. I wonder if whoever looks after this list could either move or gateway it to a usenet group? That would also eliminate the need for special purpose archiving and searching facilities since the site: http://groups.google.com would automatically provide that. That site also

I am in the process of setting up R1.3.1 on a new computer running windows 2000. I am having problems running the PFE text editor simultaneously within R for editing functions and outside R for editing ordinary text files. The PFE editor behaves as I expected, if it is opened in R AND but no other PFE window is open outside R. Similarly, it also works fine if I am editing a text file outside

Dear all, I have a question about the chisq.test command. As an option one can chose the computation of p-values by Monte-Carlo simulation (simulate.p.value=T). Is there any documentation available how this calculations are done and how this simulation based test behaves in small samples? Thanks Klaus Abberger University of Konstanz, Germany [[alternate HTML version deleted]]

(I sent this earlier, but it seems not to have come through, due to problems witkh my system) The following command from appendix A, "a sample session", isnt correct: contour(x, y, fa, nint=15) when used R protests: Warning message: parameter "nint" couldn't be set in high-level plot() function it should probably be nlevels, as used a few lines before. This is

chisq.test with simulate.p.value=TRUE uses the Patefield algorithm, this is not documented, and the original reference is not given, as it ought to be. The reference is: Patefield,W. M. (1981) An efficient method of generating r * c tables with given row and column totals (algorithm AS 159). Applied Statistics 30, 91-97. Kjetil Halvorsen

Hola! look at the following: > test <- function() { + options(warn=-1) + on.exit( options(warn=0)) + log(-1) + } > test() [1] NaN but what should be better, doesnt work: > test1 <- function() { + oldwarn <- options("warn") + options(warn=-1) + on.exit( options(warn=oldwarn)) + log(-1) + } > test1() Error in options(...) : warn parameter

> From: kjetil halvorsen [mailto:kjetilh at umsanet.edu.bo] > > Martin Hoyle wrote: > > > > Dear Greg, > > Thanks for the new release. The decomposition of the SSQ is > just what I need! > > > I thought decomposition of the SSQ can be obtained with the split= > argument to summary.aov? That argum...

Hola! > rm(list=ls(all=TRUE)) > x <- 1:20 > y <- 1+x+rnorm(x) > xy.coords(y ~ x,NULL) ... expected output, correct, but when called from inside lowess: > lowess(y ~ x) Error in xy.coords(x, y) : x and y lengths differ > debug(xy.coords) > lowess(y ~ x) debugging in: xy.coords(x, y) ... long listing deleted if (is.language(x)) { if (inherits(x,

I reported this earlier, and have got reports that others have the same promlem on UNIX machines, so it is not only a windows problem S I file a bug report. The function (boot.stat) given at the end produces a postscript file, which cannot be included correctly in LaTeX. Specifically, the image in LaTeX (when translated by dvips to postscript) becomes very small, not using the bounding box, and

I am resubmitting this to r-bugs, since Thomas Lumley indicates that it might be an error: On Wed, 5 Jul 2000, Thomas Lumley wrote: > On Wed, 5 Jul 2000, halvorsen wrote: > > > Hola! > > > > I have the following simple function: > > > > > testcar > > function(pow){ > > ob <- glm(Pound~CG+Age+Vage,data=car,weights=No, > >

Hello, I'm using bwplot to make a few plots. The plots are exactly what I need, but are coming out with a grey background and turquoise boxes and whiskers. I cannot figure out how to just get black and white to be the default. Can anyone help me with this? Thanks Kenneth E. Nussear Phone 775 784-1703 Ecology, Evolution and FAX 775 784-1369

...s From: Peter Dalgaard BSA <pd@pubhealth.ku.dk> Date: Wed, 27 Jun 2001 11:54:06 +0200 * PR# 1045 * Subject: Palette changes on redraw From: Peter Dalgaard BSA <p.dalgaard@biostat.ku.dk> Date: 08 Aug 2001 19:08:01 +0200 * PR# 1147 * Subject: postscript problem From: kjetil halvorsen <kjetilh@umsanet.edu.bo> Date: Fri, 26 Oct 2001 15:23:45 -0400 --This seems to be a problem with screen/layout rather than postscript. * PR# 1161 * Subject: x-axis label in persp() From: Rolf Turner <rolf@maths.uwa.edu.au> Date: Wed, 7 Nov 2001 18:07:22 +0800 (WST) * PR# 1207 * Subject: boxplot lab...

...s From: Peter Dalgaard BSA <pd@pubhealth.ku.dk> Date: Wed, 27 Jun 2001 11:54:06 +0200 * PR# 1045 * Subject: Palette changes on redraw From: Peter Dalgaard BSA <p.dalgaard@biostat.ku.dk> Date: 08 Aug 2001 19:08:01 +0200 * PR# 1147 * Subject: postscript problem From: kjetil halvorsen <kjetilh@umsanet.edu.bo> Date: Fri, 26 Oct 2001 15:23:45 -0400 --This seems to be a problem with screen/layout rather than postscript. * PR# 1161 * Subject: x-axis label in persp() From: Rolf Turner <rolf@maths.uwa.edu.au> Date: Wed, 7 Nov 2001 18:07:22 +0800 (WST) * PR# 1207 * Subject: boxplot lab...

...s From: Peter Dalgaard BSA <pd@pubhealth.ku.dk> Date: Wed, 27 Jun 2001 11:54:06 +0200 * PR# 1045 * Subject: Palette changes on redraw From: Peter Dalgaard BSA <p.dalgaard@biostat.ku.dk> Date: 08 Aug 2001 19:08:01 +0200 * PR# 1147 * Subject: postscript problem From: kjetil halvorsen <kjetilh@umsanet.edu.bo> Date: Fri, 26 Oct 2001 15:23:45 -0400 --This seems to be a problem with screen/layout rather than postscript. * PR# 1161 * Subject: x-axis label in persp() From: Rolf Turner <rolf@maths.uwa.edu.au> Date: Wed, 7 Nov 2001 18:07:22 +0800 (WST) * PR# 1207 * Subject: boxplot lab...

...s From: Peter Dalgaard BSA <pd@pubhealth.ku.dk> Date: Wed, 27 Jun 2001 11:54:06 +0200 * PR# 1045 * Subject: Palette changes on redraw From: Peter Dalgaard BSA <p.dalgaard@biostat.ku.dk> Date: 08 Aug 2001 19:08:01 +0200 * PR# 1147 * Subject: postscript problem From: kjetil halvorsen <kjetilh@umsanet.edu.bo> Date: Fri, 26 Oct 2001 15:23:45 -0400 --This seems to be a problem with screen/layout rather than postscript. * PR# 1161 * Subject: x-axis label in persp() From: Rolf Turner <rolf@maths.uwa.edu.au> Date: Wed, 7 Nov 2001 18:07:22 +0800 (WST) * PR# 1207 * Subject: boxplot lab...

Hola! I have the following simple function: > testcar function(pow){ ob <- glm(Pound~CG+Age+Vage,data=car,weights=No, subset=No>0,family=quasi(link=power(pow),var=mu^2)) deviance(ob) } But trying to run it gives: > testcar(1/2) Error in power(pow) : Object "pow" not found I have tried to use debug on testcar, but what I can find