A Practical Proactive Proposal for Dealing with Attrition: Alternative Approaches and an Empirical Example

• 成果类型: Article
• 署名作者: DiNardo, John; Matsudaira, Jordan; McCrary, Justin; Sanbonmatsu, Lisa
• 署名单位: University of Michigan System; University of Michigan; Columbia University; National Bureau of Economic Research; Harvard University
• 刊物名称: JOURNAL OF LABOR ECONOMICS
• ISSN/ISSBN: 0734-306X
• DOI: 10.1086/712922
• 发表日期: 2021
• 页码: S507-S541
• 关键词: nonparametric-estimation; randomized trials; consort statement; sample selection; identification; opportunity; QUALITY; models

摘要

Survey nonresponse and attrition undermine the validity of many and possibly most econometric estimates. We propose that survey administrators and evaluators proactively create an instrument for observation, for example, by ex ante randomizing participants to differing intensity of follow-up. We illustrate how to apply our proposed methodology using a carefully conducted randomized controlled trial, the Moving to Opportunity demonstration project, which de facto randomly assigned a subset of subjects to more intensive follow-up. The approach yields treatment effect estimates similar to the unbiased estimator based on complete administrative data and has narrower confidence intervals than alternative bounding approaches.