[R] Error in nlme with factors in R 2.4.1

[Prof Brian Ripley]

HERBICIDE is already a factor, and this works without the unneeded 
factor() calls.

Notice that you used a different version of nlme in R 2.4.0 and R 2.4.1, 
so you have not established that the change in R version is responsible.
In fact, it is not: it is caused by the update of nlme to 3.1-78 and 
AFAICS by this change (r4013)

2006-12-06  Douglas Bates  <bates at stat.wisc.edu>

         * R/nlme.R (contrMat): Ensure that the constrasts component is a
         list of matrices by expanding function names if necessary.


On Tue, 20 Mar 2007, Christian Ritz wrote:

> Hi,
>
> the following R lines work fine in R 2.4.0, but not in R 2.4.1 or any devel versions of R
> 2.5.0 (see below for details).
>
>
> library(drc)  # to load the dataset 'PestSci'
>
> library(nlme)
>
>
> ## Setting starting values
> sv <- c(0.43355869, 2.49963220, 0.05861799, 1.73290589, 0.38153146, 0.24316978)
>
>
> ## No error
> m1 <-
> nlme(SLOPE ~ c + (d-c)/(1+exp(b*(log(DOSE)-log(e)))),
> fixed = list(b+c+d+e~1),
> random = d~1|CURVE,
> start = sv[c(2:5)], data = PestSci)
>
>
> ## No error
> m2 <- nlme(SLOPE ~ c + (d-c)/(1+exp(b*(log(DOSE)-log(e)))),
> fixed = list(b~HERBICIDE, c+d+e~1),
> random = d~1|CURVE,
> start = sv[c(1:5)], data = PestSci)
>
>
> ## Error in R 2.4.1!
> m3 <-
> nlme(SLOPE ~ c + (d-c)/(1+exp(b*(log(DOSE)-log(e)))),
> fixed = list(b~factor(HERBICIDE)-1, c~1, d~1, e~factor(HERBICIDE)-1),
> random = d~1|CURVE,
> start = sv, data = PestSci)
>
> Error in dimnames(data) <- dimnames : length of 'dimnames' [1] not equal to array extent
>
>
> An ensuing call to traceback() yields:
>
> 7: array(0, c(n, n), list(levs, levs))
> 6: contr.treatment(n = 0)
> 5: do.call(contr[[nm]], list(n = length(levs)))
> 4: FUN("factor(HERBICIDE)"[[1]], ...)
> 3: lapply(nms, contrMat, contr = contr, data = dataMix)
> 2: nlme.formula(SLOPE ~ c + (d - c)/(1 + exp(b * (log(DOSE) - log(e)))),
>        fixed = list(b ~ factor(HERBICIDE) - 1, c ~ 1, d ~ 1, e ~
>            factor(HERBICIDE) - 1), random = d ~ 1 | CURVE, start = sv,
>        data = PestSci)
> 1: nlme(SLOPE ~ c + (d - c)/(1 + exp(b * (log(DOSE) - log(e)))),
>        fixed = list(b ~ factor(HERBICIDE) - 1, c ~ 1, d ~ 1, e ~
>            factor(HERBICIDE) - 1), random = d ~ 1 | CURVE, start = sv,
>        data = PestSci)
>
>
>
>
>
> Output from sessionInfo() for R 2.4.0
>
> R version 2.4.0 (2006-10-03)
> i386-pc-mingw32
>
> locale:
> LC_COLLATE=Danish_Denmark.1252;LC_CTYPE=Danish_Denmark.1252;LC_MONETARY=Danish_Denmark.1252;LC_NUMERIC=C;LC_TIME=Danish_Denmark.1252
>
> attached base packages:
> [1] "methods"   "stats"     "graphics"  "grDevices" "utils"     "datasets"
> [7] "base"
>
> other attached packages:
>      drc  plotrix     nlme     MASS  lattice
>  "1.0-7"  "2.1-1" "3.1-77" "7.2-29" "0.14-9"
>
>
> Output from sessionInfo() for R 2.4.1
>
> R version 2.4.1 (2006-12-18)
> i386-pc-mingw32
>
> locale:
> LC_COLLATE=Danish_Denmark.1252;LC_CTYPE=Danish_Denmark.1252;LC_MONETARY=Danish_Denmark.1252;LC_NUMERIC=C;LC_TIME=Danish_Denmark.1252
>
> attached base packages:
> [1] "stats"     "graphics"  "grDevices" "utils"
> [5] "datasets"  "methods"   "base"
>
> other attached packages:
>       drc   plotrix      nlme      MASS   lattice
>   "1.0-7"   "2.1-6"  "3.1-78"  "7.2-30" "0.14-16"
>
>
>
>
>
>
> Christian
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

-- 
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 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595