[R-sig-ME] Error with glmer when nesting students in school

Ken Beath ken at kjbeath.com.au
Fri Jul 10 07:29:06 CEST 2009


I expect this is the same as https://stat.ethz.ch/pipermail/r-sig-mixed-models/2009q1/002081.html

I can understand Dougs reluctance to change this, as it would allow  
some silly things. A compromise might be to improve the error message  
to explain that lmer thinks the model is overparameterised and allow  
the user to force these models to be fitted. eg forcefit=TRUE as a  
parameter.

Ken


On 10/07/2009, at 5:24 AM, Christopher David Desjardins wrote:

> Hi,
> I am running a model where my outcome variable is a count variable  
> (# of suspensions) and I am trying to nest students (id.f) within  
> school (schno.f). When I run this model I get the following error:
>
> glmer.quad.sch <- glmer(sus ~ (grade)^2 + male*(grade)^2 +  
> sped*(grade)^2 + ethnic*(grade)^2 + risk*(grade)^2 + (1+ (grade)^2 |  
> schno.f/id.f), family=poisson, nAGQ=1, data= enroll.long.ting)
> Error message:
> Error in mer_finalize(ans) : q = 209642 > n = 175975
> Calls: system.time ... glmer -> do.call -> <Anonymous> ->  
> mer_finalize -> .Call
> Execution halted
>
> I am treating both id.f and schno.f as factors as glmer wouldn't run  
> without them.
> Thanks,
> Chris
>
> > sessionInfo()
> R version 2.9.1 (2009-06-26)
> i386-apple-darwin8.11.1
>
> locale:
> en_US.UTF-8/en_US.UTF-8/C/C/en_US.UTF-8/en_US.UTF-8
>
> attached base packages:
> [1] stats     graphics  grDevices utils     datasets  methods   base
>
> other attached packages:
> [1] lme4_0.999375-31   Matrix_0.999375-29 lattice_0.17-25
>
> loaded via a namespace (and not attached):
> [1] grid_2.9.1
>
>
> -- 
> Christopher David Desjardins
> Ph.D. Student
> Quantitative Methods in Education
> Department of Educational Psychology
> University of  Minnesota
> http://cddesjardins.wordpress.com/
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>




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