G'day, The following code gives a two-way factorial anova, which is completely balanced. However when model.tables is called, the response is: "Design is unbalanced - use se.contrasts for se's", and SEs are not available. Why doesn't R think my design is balanced and how do I convince it that it is and get the SEs that I want? response<-c(rnorm(5,5,2),rnorm(5,12,2),rnorm(5,18,2),rnorm(5,12,2)) factor1<-factor(rep(c(1,2),each=10)) factor2 <- factor(rep(rep(c(1,2),each=5),2)) ddmodel<-aov(response~factor1*factor2) summary(ddmodel) model.tables(ddmodel, type="means",se=T) Don. Dr Don Driscoll Lecturer in Biodiversity School of Biological Sciences Flinders University GPO Box 2100 Adelaide SA 5001 (08) 8201 2165