Dear all, I have a problem finding how to use properly prior.weights and weights options when performing a stepwise GAM analysis (gam and step.gam functions of GAM package) for covariate inclusions. The code I use is coming from the documentation and I do not get any error messages but not expected results. Just want to know if some people have experience using these 2 options in GAM package (or even in glm). Thanks beforehand for references or help on how to handle these 2 options. -- Paul Baverel, MSc, PhD student Div. of Pharmacokinetics and Drug Therapy, Dept. of Pharmaceutical Biosciences, Faculty of Pharmacy Uppsala University