Hi all, I am interested in understanding the effect of various predictor variables on the spread of a given response variable. I know how to use permutation tests to compare spreads between two groups, but I am wondering if there is some way to create something like a regression model using either permutation or bootstrap methods that will perform reasonably for studying the effect of predictors on spread. Does anyone know of such an approach? Thanks, Eugenie You may leave the list at any time by sending the command SIGNOFF allstat to [log in to unmask], leaving the subject line blank.