Beyond Differences: Doubly Robust Meta-Learners for Ratio-Based Treatment Effects

Michael Fuchs, Dominik Kreiss

When treatment effects are naturally expressed as ratios -- as in medicine, pricing, and marketing -- the ratio-based CATE $\ddot{I}„(x)=E[Y|W=1,X=x]/E[Y|W=0,X=x]$ is the appropriate…