Hello forum, I am interested in investigating non-linear relationships between variables using something akin to Multivariate Adaptive Regression Splines. The problem is that my data have sample weights and stratification variables, and I don't think earth and similar packages support these. Any suggestions? It doesn't have to be MARS per se, just something to estimate non-linear relationships that does a better job than polynomials and can incorporate sample weights and stratification variables. Thanks, Jim -- View this message in context: http://r.789695.n4.nabble.com/MARS-for-complex-survey-data-tp3580659p3580659.html Sent from the R help mailing list archive at Nabble.com.