Press "Enter" to skip to content

Finding Omitted Variables in Logistic Regression

John Mount picks up on a prior post:

For this note, let’s work out how to directly try and overcome the omitted variable bias by solving for the hidden or unobserved detailed data. We will work our example in R. We will derive some deep results out of a simple set-up. We show how to “un-marginalize” or “un-summarize” data.

This is an interesting dive into a common problem, and something which we can easily work around in linear regression, but not in logistic regression.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.