Affiliations: [a] Dept. of Economics, University of Wisconsin –
Madison, 1180 Observatory Dr., Madison, WI 53706, USA
Note: [1] Presented at the Conference on the Future of SIPP, 11 April 1991.
Abstract: SIPP is now in its ninth year of data collection. Measurements collected have
advanced understanding of poverty, program eligibility, and simulation of
alternatives to the current tax and transfer programs of the U.S. At the same
time, nine years of measurement disclose limitations for the scientific design
that is currently used. Inconsistencies in the responses collected in different
interviews (the seam problem), the large number of censored spells during which
respondents are eligible for welfare, or receive welfare transfers, and the
failure of analysts to exploit identical measures taken from independent samples
that are taken in the same month all point to the need to rethink the scientific
design for SIPP. This paper presents a framework for thinking about a new
design; the framework integrates the underlying purposes of SIPP, thinking about
troublesome problems of response error, and constraints in the operational
aspects of large surveys. SIPP can provide measurements for the study of the change in the economic
well-being of individuals. Analysis of SIPP can service legislation and
administration affecting social services, income support, a work role, and
taxation for persons with the least capabilities and opportunities in the
society. Other purposes can be met by SIPP, and readers will be able to test
their own objectives for a social and economic measurement within the framework
that follows.
