2003 National Survey of College Graduates Nonresponse Bias Analysis

• Activity Number: 313
• Type: Contributed
• Date/Time: Tuesday, August 3, 2010 : 8:30 AM to 10:20 AM
• Sponsor: Section on Survey Research Methods
• Author(s): Michael White*+
• Companies: U.S. Census Bureau
• Keywords: survey ; nonresponse ; estimation bias ; longitudinal ; sample ; response rate

Abstract

The National Survey of College Graduates (NSCG) is a longitudinal survey that collects information on employment, educational, and demographic characteristics of the US college-educated science and engineering workforce. The NSCG refreshes its sample every decade. In the first year of the 2000 decade longitudinal panel, the NSCG experienced a 73% response rate. In response, we conducted a nonresponse bias study to assess the potential impact of nonresponse on the NSCG survey estimates. The study included a benchmark analysis, a comparison of response rates across subgroups, an evaluation of nonresponse weighting adjustments, and an evaluation of the impact data collection effort has on estimates. The goal of this study is to better understand the presence of nonresponse bias in the 2000 decade NSCG and to use the findings to assist in sample design planning for the 2010 NSCG and beyond.