[R-sig-ME] Complete separation example

[Vincent Dorie]

Thanks Jarrod, but I'm specifically looking for something where a mixed model is appropriate. My googling has shown me that it happens often enough, but I haven't found much with available data.

On Mar 4, 2014, at 12:28 PM, Jarrod Hadfield wrote:

> Hi Vince,
> 
> Sex effect on horn type in Soay sheep is completely separated (the trait is partly sex-limited):
> 
> data(SShorns)
> m1<-glm(I(horn=="polled")~sex, data=SShorns, family=binomial)
> 
> Cheers,
> 
> Jarrod
> 
> 
> Quoting Vincent Dorie <vjd4 at nyu.edu> on Tue, 4 Mar 2014 12:20:41 -0500:
> 
>> Hi list, can anyone point me to a data set that exhibits complete or quasi-complete separation when fit as a glmm? It's for a vignette, so something public would be ideal.
>> 
>> With thanks,
>> Vince
>> _______________________________________________
>> R-sig-mixed-models at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>> 
>> 
> 
> 
> 
> -- 
> The University of Edinburgh is a charitable body, registered in
> Scotland, with registration number SC005336.
> 
>