Step-Wise Regression

1101140001
1101140001 New Altair Community Member
edited November 5 in Community Q&A

Anyone knows how to perform a Step-wise Regression with RM?
Which would be the right operator? or would I need to install a specific extension?

Thanks...

Answers

  • Telcontar120
    Telcontar120 New Altair Community Member

    If you are looking for a classic stepwise regression, you can use either Forward Selection or Backward Elimination operators, which are both part of the feature selection operator folder, and use Linear Regression as the inner learner.  You can set the selection logic either based on absolute change in performance or associated alpha values.

     

     

  • 1101140001
    1101140001 New Altair Community Member

    @Telcontar120 This ise step-wise regression algortihm but I don't understand,must I use forward or backward elimination. 

    Stepwise.jpg

  • Telcontar120
    Telcontar120 New Altair Community Member

    This graphic depicts forward selection.  It also envisions adding all cross-product terms (2nd order interactions) and potentially even higher-order interactions.  I'm not sure where you are getting this guidance, but it certainly doesn't represent state-of-the-art best practices for model construction in modern data science, in my view.  I'd be very wary of overfitting if you blindly dump all these interactions terms into a regression framework without doing any kind of feature engineering or feature selection.