Estimating the Impacts of Program Benefits: Using Instrumental Variables with Underreported and Imputed Data

Melvin Stephens; Takashi Unayama

doi:10.1162/rest_a_00769

← Search

Estimating the Impacts of Program Benefits: Using Instrumental Variables with Underreported and Imputed Data

Melvin Stephens¹; Takashi Unayama²

¹ University of Michigan and NBER · ² Hitotsubashi University

The Review of Economics and Statistics 2019

Survey nonresponse has risen in recent years, which has increased the share of imputed and underreported values found on commonly used data sets. While this trend has been well documented for earnings, the growth in nonresponse to government transfers questions has received far less attention. We demonstrate analytically that the underreporting and imputation of transfer benefits can lead to program impact estimates that are substantially overstated when using instrumental variables methods to correct for endogeneity or measurement error in benefit amounts. We document the importance of failing to account for these issues using two empirical examples.

DOI: 10.1162/rest_a_00769
Volume: 101 (3)
Pages: 468-475
Language: en
Export: BibTeX
Sources: openalex crossref