[R-sig-ME] how reliable are inferences drawn from binomial models for small datasets fitted with lme4?

Roger Levy rlevy at ling.ucsd.edu
Mon Jul 6 22:54:48 CEST 2009


On Jul 5, 2009, at 12:51 PM, Roger Levy wrote:

> This post may be of interest in light of the recent discussion of  
> PQL versus Laplace-approximated likelihood.

Oh dear, I made a mistake in posting the original dataset -- I posted  
the hypothesized dataset where I had converted one Treatment-2 success  
to failure, rather than the original data.  This line:

>    Treatment F1 F2 Response
> ...
> 142         2  1  7        0
> ...


should have been

>    Treatment F1 F2 Response
> ...
> 142         2  1  7        1
> ...

Apologies to all...

Best

Roger




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