Just a note on the limma prior: In my current microarray study, the MSEs from the ordinary ANOVA are a very good fit to a LogNormal. They are not a very good fit to the scaled chi-square distribution that is fitted by limma (although I concede that this probably does not matter). Naomi S. Altman 814-865-3791 (voice) Associate Professor Bioinformatics Consulting Center Dept. of Statistics 814-863-7114 (fax) Penn State University 814-865-1348 (Statistics) University Park, PA 16802-2111