I am working on a regression model and I have 26 features. I want to select a subset of important/significant features, not necessarily the ones that help prediction. In other words I want to find a subset of features such that the number of features with p_value < 0.001 is maximized. I found different feature selection methods but none of them use p-values of features.

  • $\begingroup$ So pick all the ones with p_value < 0.001. I don't recommend it, but I don't really understand your question. $\endgroup$ – C8H10N4O2 Oct 20 '15 at 20:12
  • 1
    $\begingroup$ Do not rely on p-values strongly; they are only indicators not control variables. Use a simple information criterion (eg. AICc) and then slow built up from there. $\endgroup$ – usεr11852 says Reinstate Monic Oct 20 '15 at 20:13
  • 2
    $\begingroup$ This doesn't seem to contain any questions at all. Please ask a question $\endgroup$ – Glen_b -Reinstate Monica Oct 20 '15 at 20:28

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.