Abstract
The Survey of Income and Program Participation (SIPP) is a potentially useful
data set to study earnings and retirement dynamics of older workers.
Respondents’ self-reported work and earnings in the SIPP are, however, likely
to be measured with error, and this measurement error may be particularly
large for older respondents who work non-standard hours. We explore the
extent of measurement error by comparing SIPP employment and earnings
data to administrative records contained in the matched Detail Earning Record.
Users
Please
log in to take part in the discussion (add own reviews or comments).