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

A PSC Brown Bag Seminar

Melvin Stephens, Jr

Monday, 11/3/2014.   ARCHIVED EVENT

Location: 6050 ISR Thompson St

Survey non-response has risen in recent years which has increased the share of imputed and underreported values found on commonly used datasets. While this trend has been well documented for earnings, the growth in non-response 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 and/or measurement error in benefit amounts. We document the importance of failing to account for these issues using two empirical examples and examine the plausibility of using straightforward methodological adjustments to generate consistent estimates.

Related Material:

Live Stream

PSC Brown Bag seminars highlight recent research in population studies and serve as a focal point for building our research community.

Forthcoming . Past . Next

PSC In The News

RSS Feed icon

Barbara Anderson comments in NYT on Federal Law that protects citizenship status data from distribution by the Census Bureau

Anderson discusses impact of Administration's ongoing pursuit of Citizenship information around the 2020 Census with Michigan Radio

Burgard correlates job insecurity higher with negative overall health and depression than the impact of job loss and regain

More News

Highlights

Colter Mitchell receives Presidential Early Career Award for Scientists and Engineers (PECASE)

Frey receives 2019 ASA Distinguished Contributions to Teaching Award

More Highlights


Connect with PSC follow PSC on Twitter Like PSC on Facebook