3
$\begingroup$

I am studying the elastic net regression and in some material I read, it was mentioned that the method will choose a group of regressors that are correlated while LASSO can pick one among the correlated variables.

My question is, if I apply elastic net, then can I still interpret the coefficients on the regressor to the dependent variable? Since multicollinearity may cause the coefficients to have opposite signs, I am concerned that I will not be able to interpret my coefficients.

$\endgroup$
2
  • 1
    $\begingroup$ I took the liberty of editing the question attempting to make it clearer. Please see if I did not change the meaning. I do not think the elastic net coefficients will suffer much from multicollinearity -- because regularization (such as elastic net or ridge regression) actually should be a sensible remedy for multicollinearity. However, I am not really qualified to answer the question. $\endgroup$ Nov 30, 2015 at 20:21
  • $\begingroup$ Thanks for the editing! It's much better now! Hope some one can answer this question! :) $\endgroup$
    – phebe wu
    Dec 2, 2015 at 20:42

0

Your Answer

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

Browse other questions tagged or ask your own question.