Working Paper: NBER ID: w19959
Authors: Guido W. Imbens
Abstract: There is a large theoretical literature on methods for estimating causal effects under unconfoundedness, exogeneity, or selection--on--observables type assumptions using matching or propensity score methods. Much of this literature is highly technical and has not made inroads into empirical practice where many researchers continue to use simple methods such as ordinary least squares regression even in settings where those methods do not have attractive properties. In this paper I discuss some of the lessons for practice from the theoretical literature, and provide detailed recommendations on what to do. I illustrate the recommendations with three detailed applications.
Keywords: No keywords provided
JEL Codes: C1
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| OLS estimation (C51) | biased estimates (C51) |
| covariate distributions differ significantly between treatment groups (C46) | biased estimates (C51) |
| matching methods (C52) | more robust estimates of treatment effects (C22) |
| adjust for covariate differences (C52) | more robust estimates of treatment effects (C22) |
| trimming of samples based on propensity scores (C24) | enhance the reliability of causal estimates (C90) |
| assessing plausibility of unconfoundedness assumption (C90) | reveal potential biases in estimating treatment effects (C21) |