This evening I ran into the problem Chuck Clifton referred to in message 86
of Volume 71 Issue 9 of this list. That is, objects created by lmer change
after calling pvals.fnc on that lmer object when using lme4
version 0.999375-16 and 0.999375-28. This is somewhat troublesome. The bug
tracker on R-Forge (
http://r-forge.r-project.org/tracker/index.php?func=detail&aid=68&group_id=60&atid=298)
<http://r-forge.r-project.org/tracker/index.php?func=detail&aid=68&group_id=60&atid=298>shows
problems with mcmc resampling as existing since November 2007. Bates has a
note there (dated 2008-06-23) in reference to .999375-16 that make it sounds
like mcmc is getting back on track, but might have small problems. My
question in short is what are the last "stable" versions of lme4 and
languageR in which I might trust my mcmc estimates and in which my lmer
object won't change?
sessionInfo:
R version 2.8.1 (2008-12-22)
i386-pc-mingw32
locale:
LC_COLLATE=English_United States.1252;LC_CTYPE=English_United
States.1252;LC_MONETARY=English_United
States.1252;LC_NUMERIC=C;LC_TIME=English_United States.1252
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] languageR_0.953 lme4_0.999375-28 Matrix_0.999375-17 zipfR_0.6-5
[5] lattice_0.17-20
loaded via a namespace (and not attached):
[1] grid_2.8.1
Thanks,
Russell PierceGraduate Student
University of California, Riverside
[[alternative HTML version deleted]]
