This question already has an answer here:

People typically prefer the Lasso or other methods to stepwise regression.

What are the main problems in stepwise regression which makes it unreliable specifically the problems with forward selection , backward elimination and Bidirectional elimination?


marked as duplicate by Ben Bolker, Michael R. Chernick, kjetil b halvorsen, Peter Flom - Reinstate Monica Aug 25 '18 at 11:31

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.


See here for a nice list of issues and search the site as this has been discussed extensively.

One of the issues is that the remaining coefficients are biased and need shrinkage which is what the LASSO and its cousins (i.e. the elastic net, ridge regression) try to achieve.


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