Identifying the Effects of a Program Offer with an Application to Head Start

TL;DR

This paper develops a treatment selection model accounting for unobserved heterogeneity to evaluate the effects of Head Start program offers, revealing positive impacts on test scores and potential economic benefits.

Contribution

It introduces a novel model that captures unobserved heterogeneity in choice sets and preferences for program evaluation, with an application to Head Start impact analysis.

Findings

Large number of children take up the offer and show positive test score effects.

Effects are driven by children without outside preschool options.

Cost-benefit analysis indicates significant earning benefits outweigh costs.

Abstract

I propose a treatment selection model that introduces unobserved heterogeneity in both choice sets and preferences to evaluate the average effects of a program offer. I show how to exploit the model structure to define parameters capturing these effects and then computationally characterize their identified sets under instrumental variable variation in choice sets. I illustrate these tools by analyzing the effects of providing an offer to the Head Start preschool program using data from the Head Start Impact Study. I find that such a policy affects a large number of children who take up the offer, and that they subsequently have positive effects on test scores. These effects arise from children who do not have any preschool as an outside option. A cost-benefit analysis reveals that the earning benefits associated with the test score gains can be large and outweigh the net costs associated with offer take up.