Abstract:
|
Recent evidence suggests that labor earnings reported in household surveys compare favorably with labor earnings in administrative records. On the other hand, imputed labor earnings in household surveys seem to match labor earnings in administrative records less closely. This finding has led many researchers to question the reliability of imputed earnings and to exclude these observations from wage analyses. However, this strategy might result in sample selection bias if earnings are not missing at random. In this paper, we compare reported and imputed earnings from the 2008 panel of the Survey of Income and Program Participation to earnings from the Social Security Administration's Detailed Earnings Record. Individuals who are earnings nonrespondents, male, more educated, self-employed, and nonrecipients of social programs have larger average deviations between survey and administrative earnings. Males, self-employed individuals, and nonrecipients of social programs are more likely to exhibit imputed earnings. We establish a novel pattern of nonresponse over the administrative earnings distribution. The implications for estimates of the earnings structure are ambiguous.
|