Non Random Selection in the HRS Social Security Earnings Sample.

The Health and Retirement Study (HRS), administered by the Institute for Social Research (ISR) at the University of Michigan, is a longitudinal survey of the population of U.S. households with at least one adult between the ages of 51 and 61 in 1992 (individuals born between 1931 and 1941). In accordance with an agreement with the Social Security Administration, HRS respondents were asked to grant ISR permission to obtain the respondents' earnings histories as reported to the Social Security Administration. Although most respondents agreed to provides ISR access to their social Security earnings records, some respondents refused. Fortunately, because the respondents that refused access to their earnings histories did respond to the HRS questionnaire, it is possible to explore whether the provision of permission is systematically related to the variables measured in the HRS. This note uses that information to explore the degree to which refusals to grant acess to the Social Security data may have damaged the representativeness of the sample of earnings histories.