[R] NLME 3 (R version) again!
Prof Brian Ripley
ripley at stats.ox.ac.uk
Mon Jul 31 14:22:37 CEST 2000
> Date: Mon, 31 Jul 2000 12:42:45 +0100
> From: Anthony Lacey <a.lacey at man.ac.uk>
> To: jcp at research.bell-labs.com, r-help at stat.math.ethz.ch
(Jose' Pinheiro is not the primary maintainer of nlme for R: should
the DESCRIPTION file be clarified to send comment to Doug Bates?)
> Well after trying to fix the assign commands in version 3.1.7 of your nlme
> I still cannot get the plot functions to work. Basically I have no other
packages installed (apart from those provided with R) so nlme is the first.
> my R version info is;
> platform sparc-sun-solaris2.7
> arch sparc
> os solaris2.7
> system sparc, solaris2.7
> major 1
> minor 1.0
> year 2000
> month June
> day 15
> language R
> I have downloaded nlme version 3_1.7 from the CRAN site.
> I have been trying the example code from the plot.gls command. However, the
plotcommand fails because the assigns use where instead of envir. So I changed
these and still recieved and error telling me that envir was being misused. From
what I could see the envir were being used in default mode so I simply removed
them. Now when I run the code I get the following;
> Loading required package: nls
> > data(Ovary)
> > fm1 <- gls(follicles ~ sin(2*pi*Time) + cos(2*pi*Time), Ovary,
> + correlation = corAR1(form = ~ 1 | Mare))
> > plot(fm1, resid(., type = "p") ~ fitted(.) | Mare, abline = 0)
>  FALSE
> (and a very blank graph screen).
example(plot.gls) does no plotting, which is a fair indication that this
is not supposed to work.
> Also if I run the following (plot.variogram example) I get the following;
Did you mean plot.Variogram?
> > data(Ovary)
> > fm1 <- lme(follicles ~ sin(2*pi*Time) + cos(2*pi*Time), Ovary)
> > plot(Variogram(fm1, form = ~ Time | Mare, maxDist = 0.7))
> Error in FUN(X[], ...) : couldn't find function "dist"
dist is in library(mva), and again the code is omitted in
> Has anybody got this code to work. I suspect looking at the code and the
calls to bwplot and xyplot (all of which are S-plus) that not all this code has
been converted. I am new to R and thus am I being niave to expect all the code
(particularly the plotting routines) to work with R?
Yes. I thought it said so in the package, but can't see it at a quick glance.
Should nlme have a STATUS or PORTING file as some other R packages do?
Brian D. Ripley, ripley at 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
r-help 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-help-request at stat.math.ethz.ch
More information about the R-help