I try to implement the boosting algorithm from Schapire/Freund. As weak learners I want to use trees with only two (stumps) or four terminal nodes. I tried in R with the package rpart and tree. With the package tree I got some troubles with weights in a classification tree. And with the rpart command I dont know how to produce a stump or a tree with a certain number of terminal nodes. My question: How can I produce with the command rpart such a tree, if the tree sould be grown "best-first" without pruning, always using weights. thanks, josef vogt -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._