Estimating the effect of treatments allocated by randomized waiting lists

TL;DR

This paper addresses the bias in estimating treatment effects from randomized waiting lists, proposing a new consistent estimator that can significantly alter previous conclusions.

Contribution

It introduces a novel estimator for causal effects in randomized waiting list settings, correcting inconsistency in traditional methods.

Findings

The traditional estimator is inconsistent due to non-comparable groups.

The proposed estimator is shown to be consistent through theoretical analysis.

Application to real data demonstrates substantial differences from previous estimates.

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. We propose a new estimator, and show that it is consistent. Finally, we revisit an application, and we show that using our estimator can lead to sizably different results from those obtained using the commonly used estimator.