S3E27: Propensity Scores -- I Meant To Do That!
Quantitude
The Problem of Multiple Coveriats in Machine Learning Models
The state of the art is a method called highly adaptive lasso, which is a form of lasso regression that operates on categorized versions of the coverats. It has this really interesting asemtotic guarantee of conver gents at a specific rate. Sometimes these machine learning models will just select out the variables that are less important to the outcome. You don't need to perform this act of variable selection yourself, or rely on dimension reduction methods,. Because a machine learning method does that automatically as part of it.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
