similar to: delete.response() incorrectly handles terms-objects (PR#1328)

Prof Brian D Ripley wrote: > > Thanks, fixed now. > > Why were you calling delete.response on an object with no response, BTW? I used it in predict.svm(), and the terms-object contained in the svm model just happens to have no response for the ``one-class classification'' if svm was called e.g. by: m <- svm(~a+b). Because of the second line in delete.response() if

On Mon, 28 Aug 2000, Rashid Nassar wrote: > Dear Professor Ripley, > > Thank you very much for your kind explanation. If I may lamely say > something in my defence, even as I apologize for my error: I mistook the > sentence "the (quoted) name of a function" to mean "optionally quoted" > because of the parentheses surrounding "quoted", and was

For the record. -----Original Message----- From: ripley@stats.ox.ac.uk [mailto:ripley@stats.ox.ac.uk] Sent: Tuesday, June 18, 2002 3:21 PM To: Warnes, Gregory R Cc: 'r-help@stat.math.ethz.ch' Subject: RE: [R] Problems with url/download and http_proxy The port is not supposed to be required, so rather than fix the docs can anyone fix the problem? On Tue, 18 Jun 2002, Warnes, Gregory R

Specifically Solaris 2.7 and R 1.2.2 patched, but the principle is general. src/unix/sys-unix.c declares the function tilde_expand from readline, incorrectly for readline 4.x. That's OK in 4.1 as it is not in the included headers, but it is for 4.2, and so compilation fails (under gcc 2.95.3 at least). The quick fix is (ca line 88) char *tilde_expand(const char*); ^^^^^

On Mon, 20 May 2002 dciemo@excite.com wrote: > Full_Name: David Ciemiewicz > Version: 1.3.1 > OS: Windows 2000 > Submission from: (NULL) (63.192.218.208) > > > In the R Language Manual (R-lang.pdf), section 3.2.1 "if", there is an example > expression which uses the function "any". > > > if( any(x) <= 0 ) y <- log(1+x) else y <- log(x)

anova() on three or more objects behaves inconsistently in R. In R anovalist.lm does a sequential ANOVA using pairwise F tests, ignoring all the other objects, so the larger of the two models provides the denominator. In S anova.lmlist uses the denominator from the largest model (smallest residual df) in the set, as does anova.glmlist in both. I suggest that R's anovalist.lm is wrong (that

Based on a report to the Windows maintainers from Richard Rowe <Richard.Rowe@jcu.edu.au>: NEWS for 1.3.0 says o Exact p-values are available for the two-sided two-sample Kolmogorov-Smirnov test. I think the (new) p-values are computed but are backwards: > set.seed(123) > x <- rnorm(50) > y <- runif(50) > ks.test(x,y, exact=T)$p [1] 1 > 1 - ks.test(x,y,

This does seem to fix my problem: > Sys.getenv("http_proxy") http_proxy "http://gproxy1.pfizer.com/" > url("http://cran.r-project.org/src/contrib/PACKAGES",'r') description "http://cran.r-project.org/src/contrib/PACKAGES" class

On Wed, 14 Aug 2002, Henrik Bengtsson wrote: > Sorry, but it was indeed the redirection of the standard output in > Cygwin/bash that cause the first problem, not R (I should stop doing > troubleshooting at 1:00 AM). So please forget about the problems reported in > R_CMD_check.out. However, it would still be nice if you still update R CMD > check to do join with "\n".

Using zero-weight values in glm returns incorrect fitted values and linear predictors, the ninth value in the following. > example(glm) > fit <- glm(counts ~ outcome + treatment, family = poisson(), data=d.AD, weights=c(rep(1,8), 0)) > fit$linear.predictor 1 2 3 4 5 6 7 8 2.989646 2.535391 2.862201 2.989646

> Date: Mon, 22 May 2000 16:52:59 +0200 (CEST) > From: Martyn Plummer <plummer@iarc.fr> > To: ripley@stats.ox.ac.uk > Subject: Re: [Rd] RE:bug 548 graphics '*' (PR#549) > Cc: R-bugs@biostat.ku.dk, r-devel@stat.math.ethz.ch > > On 22-May-00 ripley@stats.ox.ac.uk wrote: > > A little more followup. The gtk() device uses gdk_string_width to > > find the

Thanks very much, Professor Ripley. Reid Huntsinger -----Original Message----- From: ripley at stats.ox.ac.uk [mailto:ripley at stats.ox.ac.uk] Sent: Tuesday, August 06, 2002 3:00 AM To: Huntsinger, Reid Cc: r-help at stat.math.ethz.ch Subject: Re: [R] pipe and binary i/o (on Linux) On Mon, 5 Aug 2002 ripley at stats.ox.ac.uk wrote: > pipe predates readBin, and no one has seen a

I can confirm this bug has been solved, by the expedient of removing the incorrect functions! I think the simplest way to get a bug closed is to send the correction to the original reporter for confirmation, then as Peter suggests send a follow-up to R-bugs. On Fri, 6 Apr 2001 p.dalgaard@biostat.ku.dk wrote: > Paul Gilbert <pgilbert@bank-banque-canada.ca> writes: > > > Peter

Filing response for the record -- Brian D. Ripley, ripley@stats.ox.ac.uk 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 272860 (secr) Oxford OX1 3TG, UK Fax: +44 1865 272595 ---------- Forwarded message ---------- Date: Thu, 21

The TITLE for the nnet package is garbled: it comes out as nnet Feed-forward neural networks and multinomial log-linear nnet Feed-forward neural networks and multinomial log-linear models The problem is in maketitle: auk% cat DESCRIPTION Bundle: VR Version: 6.1-9 Date: 2000/07/11 Depends: R (>= 1.1) Author: S original by Venables & Ripley. R port by Brian Ripley

There seems to be a bug in "dotplot" concerning the "cex" parameter. Setting cex has no effect on the character size of the labels of the points. This problem was posted to r-help today (Thu, 18 Jan 2001); the solution given by Brian Ripley (and Uwe Ligges) seems to work for me. Heinrich Rinner. > version _ platform i386-pc-mingw32 arch x86

This message is in MIME format. The first part should be readable text, while the remaining parts are likely unreadable without MIME-aware tools. Send mail to mime@docserver.cac.washington.edu for more info. ------=_NextPart_000_0006_01C2432C.7ACD6BA0 Content-Type: TEXT/PLAIN; CHARSET=iso-8859-1 Content-Transfer-Encoding: 8BIT Content-ID: <Pine.GSO.4.44.0208140920312.15226@auk.stats>

This example is caused by R's messing with formula environments. That's explained in ?formula, but should it not be explained in ?model.frame ? Simple test: data <- data.frame(y=rnorm(100), x=1:100) testit <- function(formula) { weights <- runif(100) glm(formula, weights=weights, data=data) } testit(y ~ x) weights is looked for in the environment of the formula, not of

Confirmation from John Maindonald. -- Brian D. Ripley, ripley@stats.ox.ac.uk 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 272860 (secr) Oxford OX1 3TG, UK Fax: +44 1865 272595 ---------- Forwarded message ---------- Date: Fri, 3

This is answered in the rw-FAQ, Q2.12! It is not a problem with R, but with your installation of Windows. *PLEASE* do not report FAQs as bugs: it a complete waste of the developers' time. On Thu, 27 Dec 2001 hb@maths.lth.se wrote: > Full_Name: Henrik Bengtsson > Version: v1.4.0 (2001-12-19) > OS: WinMe > Submission from: (NULL) (217.208.14.137) > > > When