[R-sig-ME] current r-forge version fails R CMD check ... ?

Ben Bolker bolker at ufl.edu
Thu Jul 30 23:30:17 CEST 2009


  When I use the latest r-forge version of lme4
(  0.999375-32 ) it seems to fail R CMD check on a tiny
numerical mismatch of two objects that are supposed
(??) to be identical (I also
get a mangled CHOLMOD error message, but I suspect that
comes from somewhere within Matrix ...)

  can anyone confirm? any ideas for a fix?

  The offending mismatch between ranef(m2) and ranef(m3)
is very small ...

> ranef(m2)
$ff
  (Intercept)          x2
1  -0.8896154  0.06947426
2   1.9253111 -0.15035662
3  -0.1315062  0.01026994
4   0.2420718 -0.01890453

> ranef(m3)
$ff
  (Intercept)          x2
1  -0.8896130  0.06947407
2   1.9253069 -0.15035628
3  -0.1315054  0.01026988
4   0.2420710 -0.01890446

  (this doesn't affect anything I'm doing directly, but
I want to build some Windows binaries of a hacked version
using the CRAN win-builder, and to do that I think it
needs to pass R CMD check ... for now I am going to
try commenting out the offending test, but that seems
like a bad idea in general ...)



> getwd()
[1] "/home/ben/lib/R/pkgs/lme4/pkg/lme4/tests"

> source("lmer-1.R",echo=TRUE)

...
> D <-  data.frame(y= rnorm(20,10), ff = gl(4,5),
                 x1=rnorm(20,3), x2=rnorm(20,7),
                 x3=rnorm(20,1))
> m0 <- lmer(y ~ (x1 + x2)|ff, data = D)
> m1 <- lmer(y ~ x1 + x2|ff  , data = D)
> m2 <- lmer(y ~ x1 + (x2|ff), data = D)
> m3 <- lmer(y ~ (x2|ff) + x1, data = D)
> stopifnot(identical(ranef(m0), ranef(m1)),
+           identical(ranef(m2), ranef(m3)),
+           inherits(tryCatch(lmer(y ~ x2|ff + x1, data = D) ....
[TRUNCATED]
CHOLMOD error: =*ᶈ1ñ¿@Á€Tôoá¶
Error: identical(ranef(m0), ranef(m1)) is not TRUE
In addition: Warning message:
In Ops.factor(ff, x1) : + not meaningful for factors

sessionInfo():

R version 2.9.1 (2009-06-26)
i486-pc-linux-gnu

locale:
LC_CTYPE=en_US.UTF-8;LC_NUMERIC=C;LC_TIME=en_US.UTF-8;LC_COLLATE=en_US.UTF-8;LC_MONETARY=C;LC_MESSAGES=en_US.UTF-8;LC_PAPER=en_US.UTF-8;LC_NAME=C;LC_ADDRESS=C;LC_TELEPHONE=C;LC_MEASUREMENT=en_US.UTF-8;LC_IDENTIFICATION=C

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base

other attached packages:
[1] MASS_7.2-47        lme4_0.999375-32   Matrix_0.999375-29
lattice_0.17-25

loaded via a namespace (and not attached):
[1] grid_2.9.1

-- 
Ben Bolker
Associate professor, Biology Dep't, Univ. of Florida
bolker at ufl.edu / www.zoology.ufl.edu/bolker
GPG key: www.zoology.ufl.edu/bolker/benbolker-publickey.asc




More information about the R-sig-mixed-models mailing list