[Rd] R CMD check [nlme|MASS] fails (PR#431)

[Douglas Bates]

Prof Brian Ripley <ripley@stats.ox.ac.uk> writes:

> > From: berwin@maths.uwa.edu.au
> > Date: Fri, 11 Feb 2000 12:58:00 +0100 (MET)
> 
> To run CMD check on MASS you need to set R_NSIZE in the environment.
> 500k should do.  MASS passes here on Solaris, Linux and Windows, if one
> is patient enough.  I will point out that information is in the on-line
> R complements, page 11.
> 
> I have just tried nlme on linux and 0.99.0 and example(nlme.formula)
> does fail there in CMD check, eventually.

Hmm.  I got it to pass on my Intel Linux machine.  I'll take another
look.

R CMD check nlme does require a large vsize and nsize and a lot of
patience but I did get

> ###--- >>> `nlme' <<<----- Nonlinear Mixed-Effects Models
> 
> 	## alias	 help(nlme)
> 	## alias	 help(nlme.formula)
> 
> ##___ Examples ___:
> 
> library(nlme)
> data(Soybean)
> ## all parameters as fixed and random effects
> fm1 <- nlme(weight ~ SSlogis(Time, Asym, xmid, scal), data = Soybean,
+             fixed = Asym + xmid + scal ~ 1, start = c(18, 52, 7.5),
+             control = list(nlmStepMax = 1.0))
> ## only Asym and xmid as random, with a diagonal covariance 
> fm2 <- nlme(weight ~ SSlogis(Time, Asym, xmid, scal), data = Soybean,
+             fixed = Asym + xmid + scal ~ 1, random = pdDiag(Asym + xmid ~ 1),
+             start = c(18, 52, 7.5))
> 
> ## Keywords: 'models'.

using 0.99.0

-- 
Douglas Bates                            bates@stat.wisc.edu
Statistics Department                    608/262-2598
University of Wisconsin - Madison        http://www.stat.wisc.edu/~bates/
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._