Weighting for External Validity

Isaiah Andrews, Emily Oster

NBER Working Paper No. 23826
Issued in September 2017, Revised in January 2018
NBER Program(s):Development Economics Program, Health Economics Program, Labor Studies Program, Technical Working Papers

External validity is a challenge in treatment effect estimation. Even in randomized trials, the experimental sample often differs from the population of interest. If participation decisions are explained by observed variables such differences can be overcome by reweighting. However, participation may depend on unobserved variables. Even in such cases, under a common support assumption there exist weights which, if known, would allow reweighting the sample to match the population. While these weights cannot in general be estimated, we develop approximations which relate them to the role of private information in participation decisions. These approximations suggest benchmarks for assessing external validity.

Acknowledgments

Machine-readable bibliographic record - MARC, RIS, BibTeX

Document Object Identifier (DOI): 10.3386/w23826

Users who downloaded this paper also downloaded* these: