NATIONAL BUREAU OF ECONOMIC RESEARCH
NATIONAL BUREAU OF ECONOMIC RESEARCH

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

Melvin Stephens, Jr., Takashi Unayama

NBER Working Paper No. 21248
Issued in June 2015
NBER Program(s):Labor Studies, Public Economics

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.

download in pdf format
   (311 K)

email paper

Machine-readable bibliographic record - MARC, RIS, BibTeX

Document Object Identifier (DOI): 10.3386/w21248

Users who downloaded this paper also downloaded* these:
Aghion, Akcigit, Bergeaud, Blundell, and Hemous w21247 Innovation and Top Income Inequality
Bodenhorn, Guinnane, and Mroz w21249 Sample-selection biases and the “industrialization puzzle”
Kane, Rouse, and Staiger w7235 Estimating Returns to Schooling When Schooling is Misreported
Bartelme and Gorodnichenko w21251 Linkages and Economic Development
Barnichon and Figura w21252 Declining Desire to Work and Downward Trends in Unemployment and Participation
 
Publications
Activities
Meetings
NBER Videos
Themes
Data
People
About

National Bureau of Economic Research, 1050 Massachusetts Ave., Cambridge, MA 02138; 617-868-3900; email: info@nber.org

Contact Us