Research Reports

The Use of Monetary Incentives in Census Bureau Longitudinal Surveys

Kathleen P. Creighton, Karen E. King, Elizabeth A. Martin

KEY WORDS: survey nonresponse, attrition, methodological experiment

ABSTRACT

The U.S. Census Bureau began using monetary incentives on an experimental basis in two of its demographic longitudinal surveys, the Survey of Income and Program Participation (SIPP) and the Survey of Program Dynamics (SPD), in the late 1990s. As in other longitudinal surveys, both SIPP and SPD had seen a steady increase in nonresponse over the life of the sample. Households selected for the SIPP 1996 panel, which concluded in March of 2000, were in sample for a total of four years with lengthy interviews at 4-month intervals. With each wave of the 1996 SIPP Panel, cumulative household nonresponse increased and reached nearly 34 percent at the end of 12 waves. We believe it would have been even higher if we had not used incentives in several waves of the panel.

Households selected for the SPD were originally interviewed in the last waves of the 1992 and 1993 SIPP panels and were recontacted for interviews in 1997 (known as the SPD "Bridge"), 1998, 1999, 2000, and will continue with 2001 and 2002 rounds of interviewing. The original SIPP households that were selected to continue into the SPD had reached a sample attrition rate of 50 percent at the conclusion of the 1998 interview cycle with 4 more contacts planned over the subsequent 4 years. With appeals to Congress from several outside data users, we implemented an incentive program in SPD beginning in 1999. In addition, we tested in 1999 and implemented in 2000 a program to recontact and attempt to interview households that had previously dropped out of sample in the 1997 interview cycle. This paper reviews the results from these experiments and programs and discusses plans for the use of monetary incentives in the SIPP and SPD in 2001.

CITATION: Kathleen P. Creighton, Karen King, and Elizabeth Martin. 2001. “The Use of Monetary Incentives in Census Bureau Longitudinal Surveys.” Pp. 289-310 in Statistical Policy Working Paper 32: 2000 Seminar on Integrating Federal Statistical Information and Processes. Washington DC: Federal Committee on Statistical Methodology, Office of Management and Budget. April 2001.

Source: U.S. Census Bureau, Statistical Research Division

Created: January 29, 2007
Last revised: January 29, 2007