Response Error in Earnings

Abstract

This article examines the problem of response error in survey earnings data. Comparing workers' earnings reports in the U.S. Census Bureau's Survey of Income and Program Participation (SIPP) to their detailed W-2 earnings records from the Social Security Administration, we employ ordinary least squares (OLS) and quantile regression models to assess the effects of earnings determinants and demographic variables on measurement errors in 2004 SIPP earnings in terms of bias and variance. Results show that measurement errors in earnings are not classical, but mean-reverting. The directions of bias for subpopulations are not constant, but varying across levels of earnings. Highly educated workers more correctly report their earnings than less educated workers at higher earnings levels, but they tend to overreport at lower earnings levels. Black workers with high earnings underreport to a Downloaded from greater degree than comparable whites, while black workers with low earnings overreport to a greater degree. Some subpopulations exhibit higher variances of measurement errors than others. Blacks, Hispanics, high school dropouts, part-year employed workers, and occupation ''switchers'' tend to misreport-both over-and underreport-their earnings rather than unilaterally in one direction. The implications of our findings are discussed.

How to Measure Retirement Age? A Comparison of Survey and Register Data

“…By analysing whether the results differ in terms of effect size, direction and statistical significance, this strategy aims at indicating whether the use of different definitions of retirement age lead to different conclusions about the determinants of retirement age. It does however not indicate whether some socio-economic groups report retirement age in a significantly different way as has been done in some methodological studies (C. H. Kim and Tamborini 2012). All analyses were performed in Stata 15.…”

Racial Disparities in Patient Activation: The Role of Economic Diversity

“…Researchers report relatively high rates of missing income data and concerns about the accuracy of income data in studies (Kim & Tamborini, 2014;Moore et al, 2000). Therefore, the baseline survey used in this study included a question on household income and a single difficulty with paying bills question, which directly assessed financial security.…”

The role of energy balance related behaviors in socioeconomic inequalities in childhood body mass index: A comparative analysis of Germany, the Netherlands, the United Kingdom, and the United States

“…Although there is accelerometer data available in the UK dataset-which is arguably more reliable than parent-reports of their children's activity levels-those data were not available in the other countries. As some studies show that social desirability bias differs by social strata (Kim and Tamborini, 2014), underreporting of unhealthy behaviours and overreporting of healthy behaviours might have been more severe in the lower educated groups (Nyberg et al, 2016). This possibly biased our results towards underestimating the contribution of PA and ST to BMI inequalities.…”