why you don't use PROC MIXED, It's easy and you can have all you ask for it...

-----Original Message----- From: EWARREN <EWARREN@CITRUS.UCR.EDU> Newsgroups: bit.listserv.sas-l To: SAS-L@LISTSERV.UGA.EDU <SAS-L@LISTSERV.UGA.EDU> Date: Tuesday, August 31, 1999 9:50 PM Subject: coefficients of variance components

>>hello everyone, >>I am using proc glm to obtain type III sums of squares >>for a mixed model with interactions between the nested factors. I would >>like to ultimately calculate variance components. i was wondering if anyone >>knew how to create an output file of the coefficients of the variance >>components from the type III expected mean squares. >>if that's not possible then does anyone know what algorith sas uses to >>calculate the coefficients of the variance components for a mixed model >>with interactions between the nested factors and a fixed effect. >>thanx, eugene warren >>Eugene Warren >>Biology Department >>Ecology and Evolution >>ewarren@citrus.ucr.edu >>787-5011 >> >Eugene Warren >Biology Department >Ecology and Evolution >ewarren@citrus.ucr.edu >787-5011