[R-sig-ME] forcing uncorrelated random effects

Claus Wilke cwilke at mail.utexas.edu
Thu Jun 11 19:58:23 CEST 2009

Dear list,

by default, lmer assumes that random effects are correlated. Is it possible to 
force them to be uncorrelated?

Specifically, assume I'm measuring cell counts in multiple patients over time, 
and want to fit the following two models:
> m1 = lmer( count ~ (1|patient)+time )
> m2 = lmer( count ~ (time|patient)+time )
Model 2 has two additional parameters over model 1, a variance of random 
slopes and a covariance of random slopes and random intercepts. How do I 
specify a model that has random slopes but no covariance between slopes and 

Thanks a lot,

Claus Wilke
Section of Integrative Biology 
 and Center for Computational Biology and Bioinformatics 
University of Texas at Austin
1 University Station C0930
Austin, TX 78712
cwilke at mail.utexas.edu
512 471 6028

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