[R-sig-ME] logLik (old-fashion way) for mixed-effects models

Gabor Grothendieck ggrothendieck at gmail.com
Thu Apr 16 15:55:14 CEST 2009


The regress package maximizes log likelihood (as well as other
criteria) for mixed models whose covariance matrix is a linear
combination of known matrices.

On Thu, Apr 16, 2009 at 5:03 AM, Christian Salas
<christian.salas at yale.edu> wrote:
> If i already fit a lm() model, i can obtain the log-likelihood [i do not
>  want to use AIC()] using the residuals from the model, and using the
>  RMSE of the model as sigma for my normal pdf. This would be in R like
>
>> sum(dnorm(-resi,mean=0,sd=sigma,log=T))  [1]
>
>  if i fit a gls model i can do the same
>
>  for a lme() model, i know that we cannot just use the same loglik model
>  [1], because they are different. I wonder if somedody already have some
> syntax in R similar to [1] but for  mixed-effects models, i mean something
> that compute the log-likelihood but without using lme() directly as
> summary(lme.obj)$AIC
>
>  thanks in advance!
>
> -------------------------------------------------------------------------------
> Christian Salas                     E-mail:christian.salas at yale.edu
> PhD candidate                       http://environment.yale.edu/salas
> School of Forestry and Environmental Studies
> Yale University                     Tel: +1-(203)-432 5126
> 360 Prospect St                     Fax:+1-(203)-432 3809
> New Haven, CT 06511-2189            Office: Room 35, Marsh Hall
> USA
>
> Yale Biometrics Lab                  http://environment.yale.edu/biometrics
>
> _______________________________________________
> 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