In matlab, classregtree can be used to implement classification and regression trees (CART) you can find this in the documentation however it's not clear what methods are used for either classification or regression, 3 methods exist:

Bagging decision trees, an early ensemble method, builds multiple decision trees by repeatedly resampling training data with replacement, and voting the trees for a consensus prediction.

A Random Forest classifier uses a number of decision trees, in order to improve the classification rate.

Boosted Trees can be used for regression-type and classification-type problems. Rotation forest - in which every decision tree is trained by first applying principal component analysis (PCA) on a random subset of the input features.

I'm tempted to say random forest but would like to clarify, does anyone know which method matlab implements for classification?

  • 1
    $\begingroup$ Your description of the 3 methods is not very accurate, and very confusing. All methods can be used for both regression and classification, not just Boosting. All methods seek to improve accuracy (not just RF), and RF is the same as Boosting, with an injection of randomization in the selection of predictors... $\endgroup$
    – Antoine
    Jun 23, 2015 at 13:28

1 Answer 1


It looks to me like classregtree is just building a tree, not using any of these methods, all of which are supplementary to tree building. That is, classregtree is implementing the methods described in Breiman et al., per the reference given in the documentation. It builds a tree and then (by default) prunes it.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.