How to handle with missing values in order to prepare data for feature selection with LASSO?

Machine Learning and Modeling
1

My situation:

  • I have to test 1700 variables
  • dependent variables: 3773 observation
  • Independent variables: more than 1700 (observation range from 1400-4000)
  • most cases in the sample and most variables have missing values.
  • Due to large number of explanatory variables, I intend to use LASSO to save time to select variables first --> then link back to literature and find some hidden dimension that dont exist in literature.

Beside LASSO, I also use multiple regression and compare the results.

My question: How can I handle missing value?

Thank you for your answer.

2

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.