An Embedded Experiment for Targeted Nonresponse Follow-Up in Establishment Surveys

• Activity Number: 171 - Predicting Attrition and Adaptive Strategies
• Type: Contributed
• Date/Time: Monday, July 31, 2017 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Stephen Kaputa* and Katherine Thompson and Jennifer Beck
• Companies: U.S. Census Bureau and U.S. Census Bureau and National Science Foundation
• Keywords: nonresponse follow-up ; unit response rate ; quantity response rate ; raction of missing information ; adaptive design

Abstract

The U.S. Census Bureau is investigating adaptive nonresponse follow-up (NRFU) strategies for single unit businesses in the 2017 Economic Census. This paper describes an embedded split-panel field experiment in the 2015 Annual Survey of Manufactures that tests two adaptive NRFU designs. With the first design, nonresponding establishments in the experimental group received a reminder letter either by certified mail (expensive) or standard mail (inexpensive) based on an optimal allocation that assigns a higher proportion of the certified letters to domains that initially have low unit response rates. This targeted allocation procedure ensures that all units receive some form of NRFU, but saves cost over the current procedure that sends a certified letter to all nonresponding units. The second studied adaptive design restricts the NRFU for the probability subsample of nonrespondents selected for the targeted allocation. In this paper, we compare the quality effects of the two studied adaptive NRFU designs examining effects on response, respondent sample balance, and collected data quality.