The 2010 National Survey of College Graduates (NSCG) Weighting

• Activity Number: 520
• Type: Topic Contributed
• Date/Time: Wednesday, August 7, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Benjamin M. Reist*+ and Michael White and David Hall
• Companies: U.S. Census Bureau and U.S. Census Bureau and U.S. Census Bureau
• Keywords: ACS ; Nonresponce ; Weight Trimming ; Paradata ; Two-Phase Sampling ; SESTAT

Abstract

The 2010 National Survey of College Graduates (NSCG) used 2009 American Community Survey (ACS) respondents as its sampling frame. This sample design afforded NSCG the opportunity to use a rich set of data available from the ACS to conduct weighting research. In particular, research on response propensity based locating and nonresponse adjustments and weight trimming benefited greatly from the ACS data. We researched response propensity models using ACS data collection paradata, as well as ACS survey data, to aid in predicting NSCG response patterns. We used education, occupation, and demographic information from the ACS to evaluate the effect of various weight trimming techniques on the mean square error for a wide range of variables. ACS' rich set of information enhanced NSCG's ability to improve our weighting methodologies and therefore produce higher quality survey estimates.