0

How to Estimate Dose-Response Curves When DoubleML Falls Short

https://towardsdatascience.com/how-to-estimate-dose-response-curves-when-doubleml-falls-short/(towardsdatascience.com)
Double machine learning (DoubleML) is a common method for estimating the effects of continuous treatments, but its standard partially linear model has significant limitations. This model assumes a linear effect, returning a single slope that can misrepresent non-linear relationships like saturating or inverted-U shaped curves. An alternative, a doubly robust dose-response estimator, is shown through simulations to more accurately capture these non-linear shapes. This alternative method is also less biased when one of its underlying machine learning models is misspecified and can be combined with partial pooling to improve estimates across hierarchical groups.
0 points•by ogg•2 hours ago

Comments (0)

No comments yet. Be the first to comment!

Have an account? Log in to join the discussion.