Working Paper: NBER ID: w26282
Authors: Clément de Chaisemartin; Luc Behaghel
Abstract: Oversubscribed treatments are often allocated using randomized waiting lists. Applicants are ranked randomly, and treatment offers are made following that ranking until all seats are filled. To estimate causal effects, researchers often compare applicants getting and not getting an offer. We show that those two groups are not statistically comparable. Therefore, the estimator arising from that comparison is inconsistent when the number of waitlists goes to infinity. We propose a new estimator, and show that it is consistent, provided the waitlists have at least two seats. Finally, we revisit an application, and we show that using our estimator can lead to significantly different results from those obtained using the commonly used estimator.
Keywords: randomized waiting lists; treatment effects; causal inference; estimation methods
JEL Codes: C21; C26
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Traditional estimators like the EO estimator (C51) | are inconsistent (C29) |
| The expected share of takers among those receiving offers (C78) | creates a bias in the estimation of treatment effects (C21) |
| Dropping the last taker from each waitlist (C78) | restores comparability (C59) |
| The DREO estimator (C51) | is consistent and asymptotically normal when the number of waitlists approaches infinity (C20) |
| The DREO estimator (C51) | yields significantly different results compared to the EO estimator (C51) |