160 – Using Adaptive Design and Collection Strategies to Improve Data Quality in Business Surveys
Strategies for Subsampling Nonrespondents for Economic Programs
Stephen J. Kaputa
U.S. Census Bureau
Laura Bechtel
U.S. Census Bureau
Daniel Whitehead
U.S. Census Bureau
Katherine Jenny Thompson
U.S. Census Bureau
Adaptive design strategies for data collection can increase the quality of response data under a reduced survey budget. In this framework, the U.S. Census Bureau is investigating nonresponse subsampling strategies, including a systematic sample of nonrespondents sorted by a measure of size, for usage in the 2017 Economic Census. Design constraints include a mandated lower bound on the Census unit response rate, along with targeted industry-specific response rates. This paper presents research on allocation procedures for subsampling nonrespondents, given a systematic subsample. We consider two approaches: (1) equal-probability sampling and (2) optimal allocation with constraints on unit response rates and sample size with the objective of selecting larger samples in industries that have initially lower response rates. Using the Annual Survey of Manufactures (ASM) sample as our original population, we present a simulation study that examines the cost, variance, relative bias, and unit response rates for the proposed allocations, assessing each procedure's sensitivity by varying the program-level sampling rate, the response mechanism, and the nonresponse adjusted estimator.