[R] proc mixed vs. lme

[Douglas Bates]

"Grathwohl,Dominik,LAUSANNE,NRC/NT" <dominik.grathwohl at rdls.nestle.com> writes:

> Dear All,
> 
> Comparing linear mixed effect models in SAS and R, I found the following
> discrepancy:
> 
>                             SAS                           R
> random statement            random subj(program);         random = ~ 1 |
> Subj
> -2*loglik                   1420.8                        1439.363
> random effects
> variance(Intercept)         9.6033                        9.604662
> variance(residual)          1.1969                        1.187553
> the first 3 fixed effects
> intercept                   83.0952                       81.10544
> ProgramCont                -3.4952                       -1.11526
> ProgramRI                  -1.9702                       -1.04517
> ...                        ...                            ...
> 
> Can somebody explain me this different results?

Different contrasts.  Try setting

options(contrasts = c(contr.SAS, contr.poly))

and doing the analysis in R again.

Note that all of these examples are available in the SASmixed package
for R.

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._