Dear R-help, I'm trying to apply machine learning methods, such as Random Forest, Boosted Trees or Multivariate Adaptive Regression Splines for supervised classification issues. In a epidemiological study, i'm dealing with high dimensional cluster-correlated data, each cluster corresponding to an household. If methods such as RF++ ou MASAL permit to deal with repeated data, I don't know how to apply Data Mining or Machine Learning methods to such problems. Any ideas ? Thanks ! Yohann Mansiaux