Comparing Item Nonresponse Rate in SIPP and SIPP-EHC: Case of Snap Eligibility Measurement

• Activity Number: 116
• Type: Topic Contributed
• Date/Time: Monday, July 30, 2012 : 8:30 AM to 10:20 AM
• Sponsor: Section on Government Statistics
• Author(s): Jeongsoo Kim*+ and Sharon I O'Donnell
• Companies: U.S. Census Bureau and U.S. Census Bureau
• Keywords: Item nonresponse ; Survey instrument ; SIPP ; SIPP-EHC ; SNAP

Abstract

The Survey of Income and Program Participation(SIPP)is a nationally representative longitudinal household survey, conducted every four months over a 48-month period. In order to improve data collection and to reduce costs, as well as the respondents' burden, the 2006 redesign initiative devised SIPP-EHC(Event History Calendar), of which one feature is to conduct a survey once a year as opposed to every four months. This paper compares the SIPP and SIPP-EHC survey instruments with respect to item nonresponses for a set of income and asset variables. Specifically, this study examines item nonresponse rate of the variables that measure SNAP eligibility: earned income, unearned income, and resources. Using logistic regression, we test two hypotheses:1)item non-responses are invariant to the type of survey instrument; and 2)the difference in the type of survey instruments is due to the improvements in the SIPP-EHC instrument. The regression analysis result shows that the instrument has a statistically significant effect on the item nonresponse rates. For example, the SIPP-EHC instrument reduced the percent of item nonresponses of Federal Supplemental Security Income about 20 percent