GenReg for variable selection Issue

nick_shelton

One of my customers is using GenReg for variable selection and has been experimenting with Lasso and Elastic Net.

Their model has 14 main effects, with their associated quadractic and interaction terms (lots of variables to examine).

After running Lasso or Elastic Net the final model created contains all terms with no terms zeroed out. The result is strange especially considering that when they run the same analysis using stepwise there are terms ommitted from the model.

 

Has anyone encountered this type of behavior before when using Lasso or Elastic Net?

 

 

nick_shelton

Thank you all for your suggestions. After a debug session with the customer and @jiancao we were finally able to make sense of their issue which was largely related to using too much data (250K rows) to train the model. The unique characteristics and volume of data was driving the model error to very small levels which then created the situation where every term started to show some level of significance (no terms zeroed out).

 

By using a smaller, equally representative dataset (15K rows), we were able to get Lasso and Elastic-Net to perform variable selection and build an useful model for their application.