.png)
315 – Sampling Strategies for Rare and Hard-to-Reach Populations
Evaluating the Consistency Between Responses to the 2010 NSCG and the 2009 ACS
Phyllis Singer
U.S. Census Bureau
Robyn Sirkis
U.S. Census Bureau
The purpose of this research was to examine the consistency of responses for similar questions asked in the American Community Survey (ACS) and the National Survey of College Graduates (NSCG) to better leverage the use of the ACS in the sample design and estimation of the NSCG. This research evaluated the ACS responses used in the NSCG sample design to determine if the current NSCG design was efficient for key statistics, and to identify new ACS responses that may strengthen the design. Additionally, this evaluation identified variables that could be used in model assisted and model-based estimation for the NSCG. The research consisted of two phases: response comparison and examination of response differences. We looked at individual responses to find patterns that lead to the inconsistency of occupation and education. This included constructing statistical models involving questionnaire responses and paradata to find covariates related to inconsistency.