R devel - Aug 2008 - incorrect usage of glmer crashes R (PR#12375)

Full_Name: susscorfa
Version: 2.7.1
OS: ubuntu
Submission from: (NULL) (129.125.177.31)


Incorrect implementation of the grouping variable in the function glmer crashes
R

a small example:

require(lme4); 
a<-data.frame(b=rpois(1000,10), c=gl(20,50), d=rnorm(1000,3),
e=rnorm(1000,5),
f=rnorm(1000,2)+5);  
glmer(b~d+f|c+(e), family=poisson, data=a)

It crashes R on debian linux (2 independant systems) as well as windows

The correct function usage is:
 glmer(b~d+f+(e|c), family=poisson, data=a)

I suppose it should just eveluate as wrong usage of a function but should not
crash R

This is about package 'lme4' and strictly speaking would not
belong to R-bugs.

But you have reported a bug indeed; thank you.
>>>>> "s" == susscorfa  <susscorfa at zonnet.nl>
>>>>>     on Thu,  7 Aug 2008 12:20:41 +0200 (CEST) writes:
    s> Full_Name: susscorfa Version: 2.7.1 OS: ubuntu Submission
    s> from: (NULL) (129.125.177.31)


    s> Incorrect implementation of the grouping variable in the
    s> function glmer crashes R

{the correct term is "segmentation fault" or "segfault"}

    s> a small example:

    s> require(lme4); 
    s> a<-data.frame(b=rpois(1000,10), c=gl(20,50), d=rnorm(1000,3),
e=rnorm(1000,5),
    s> f=rnorm(1000,2)+5);  
    s> glmer(b~d+f|c+(e), family=poisson, data=a)

Yes, indeed this segfaults;  similarly for lmer().

The development version of the 'lme4' package (on R-forge) no
longer does so since a few minutes ago.


    s> It crashes R on debian linux (2 independant systems) as well as
windows

    s> The correct function usage is:
    s> glmer(b~d+f+(e|c), family=poisson, data=a)

    s> I suppose it should just eveluate as wrong usage of a
    s> function but should not crash R

Yes, it now gives an error message about the incorrect
specification.

Martin Maechler, ETH Zurich