I've tried in vain to find references for converting parameter estimates from growth curve models (estimated using SAS PROC MIXED) into effect size estimates. Any help, direction, or references anyone could provide would be most appreciated. In particular, I'm using growth curve models to determine if there are differences between two treatments over time. How do I convert the difference in the slopes of the two treatments (as revealed in the fixed effects estimate for the treatment*time interaction) into something like d-type effect size? I can't seem to figure out what I should use as a denominator. -thanks.