A Simple Approximation for Evaluating External Validity Bias
We develop a simple approximation that relates the total external validity bias in randomized trials to (i) bias from selection on observables and (ii) a measure for the role of treatment effect heterogeneity in driving selection into the experimental sample.
This paper was previously circulated under the title “Weighting for External Validity.” Sophie Sun provided excellent research assistance. We thank Nick Bloom, Guido Imbens, Matthew Gentzkow, Peter Hull, Larry Katz, Ben Olken, Jesse Shapiro, Andrei Shleifer seminar participants at Brown University, Harvard University and University of Connecticut, and an anonymous reviewer for helpful comments. Andrews gratefully acknowledges support from the Silverman (1978) Family Career Development chair at MIT, and from the National Science Foundation under grant number 1654234. The views expressed herein are those of the authors and do not necessarily reflect the views of the National Bureau of Economic Research.
Isaiah Andrews & Emily Oster, 2019. "A simple approximation for evaluating external validity bias," Economics Letters, vol 178, pages 58-62.