Re: [R] Bug in predict.lm?

2013-11-16 Thread jlh.membership
day25 svn rev63987 language R version.string R version 3.0.2 (2013-09-25) nickname Frisbee Sailing ** -Original Message- From: peter dalgaard [mailto:pda...@gmail.com] Sent: Saturday, November 16, 2013 4:

Re: [R] Bug in predict.lm?

2013-11-16 Thread peter dalgaard
On 16 Nov 2013, at 03:06 , Charles Berry wrote: > Rolf Turner auckland.ac.nz> writes: > >> >> >> I *do* see the same phenomenon that Bert describes and the code of >> predict.lm() >> *does* appear to contain a bug. There is a line: >> > [snip] > >> >> The operative difference between my

Re: [R] Bug in predict.lm?

2013-11-15 Thread Charles Berry
Rolf Turner auckland.ac.nz> writes: > > > I *do* see the same phenomenon that Bert describes and the code of > predict.lm() > *does* appear to contain a bug. There is a line: > [snip] > > The operative difference between my set-up and Chuck's is that I am using > version 3.0.2 Patched. So

Re: [R] Bug in predict.lm?

2013-11-15 Thread Charles Berry
Charles Berry ucsd.edu> writes: > > Bert Gunter gene.com> writes: > [snip] > > I do not see this (see below). > > Maybe traceback() or options(recover=browser) to get > to the bottom?? Argh! I meant: options(error = recover) [rest deleted] ___

Re: [R] Bug in predict.lm?

2013-11-15 Thread Duncan Murdoch
On 13-11-15 11:57 AM, Bert Gunter wrote: Yes, I realize that it is more likely a misunderstanding on my part. Suitable humility will be tendered if this is pointed out. The claimed "bug" is that predict.lm throws an error when the scale argument is specified with interval = "conf" (and in some

Re: [R] Bug in predict.lm?

2013-11-15 Thread Toth, Denes
The same problem appears on a 64-bit linux: platform x86_64-pc-linux-gnu arch x86_64 os linux-gnu system x86_64, linux-gnu status major 3 minor 0.2 year 2013 month 09 day25 svn rev63987 language R ve

Re: [R] Bug in predict.lm?

2013-11-15 Thread Rolf Turner
I *do* see the same phenomenon that Bert describes and the code of predict.lm() *does* appear to contain a bug. There is a line: XRinv <- if (missing(newdata) && is.null(w)) But "w" gets assigned (as object$weights) only if (is.null(scale)). If that assignment is moved outside of the appl

Re: [R] Bug in predict.lm?

2013-11-15 Thread Charles Berry
Bert Gunter gene.com> writes: > > Yes, I realize that it is more likely a misunderstanding on my part. > Suitable humility will be tendered if this is pointed out. > > The claimed "bug" is that predict.lm throws an error when the scale > argument is specified with interval = "conf" (and in som

[R] Bug in predict.lm?

2013-11-15 Thread Bert Gunter
Yes, I realize that it is more likely a misunderstanding on my part. Suitable humility will be tendered if this is pointed out. The claimed "bug" is that predict.lm throws an error when the scale argument is specified with interval = "conf" (and in some other cases): > z <- lm(rnorm(10)~I(1:10))