search for: unpenalised

...del with the interaction term against the model that just contains the two main terms). I understand that the most appropriate way to do this is to use an un-penalised model for p-value estimation. Thanks, Alice -- View this message in context: http://r.789695.n4.nabble.com/Help-with-using-unpenalised-te-smooth-in-negative-binomial-mgcv-gam-tp4672141.html Sent from the R help mailing list archive at Nabble.com.