Proc MIXED

PROC MIXED provides easy accessibility to numerous mixed linear models. In the style of the GLM procedure (which uses the traditional method of ordinary least squares, or a decomposition of the sum squares,), PROC MIXED uses maximum likelihood estimation method to fit the specified mixed linear model and produce appropriate statistics. The MIXED procedure is subsumed by the GLIMMIX procedure in the following sense: 

• Linear mixed models are a special case in the family of generalized linear mixed models; a linear mixed model is a generalized linear mixed model where the conditional distribution is normal and the link function is the identity function.

• Most models that can be fit with the MIXED procedure can also be fit with the GLIMMIX procedure.

* Modeling between and within subject covariance;

proc mixed data=longi_count 

            covtest 

            cl 

            noclprint=3 

            convh=1e-7; 

class var3 var4;

model var10= var1 var2 var3 var4 var3*var4 

            /cl

            solution 

            ddfm=bw

            notest;

random intercept year  /type=un

                        sub=id_created

                        g

                        solution

                        outp=pred1r

                        outpm=pred1f;

repeated period /type=ar(1)

                 subject=id_created

                 r;

run;