Stop Chasing Your Tail: Reining in Hard-to-Reach Respondents

• Activity Number: 303
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 8:30 AM to 10:20 AM
• Sponsor: Survey Research Methods Section
• Author(s): Paul Guerino*+ and Ryan Hubbard
• Companies: Centers for Medicare and Medicaid Services and Westat
• Keywords: responsive design ; refusal conversion ; contact attempts ; survey costs ; adaptive design ; data collection

Abstract

The Medicare Current Beneficiary Survey (MCBS) produces nationally representative estimates of health status, health care use and expenditures, health insurance coverage, and socioeconomic characteristics of Medicare beneficiaries. It is a large-scale, national survey with a rotating panel design and two decades of history spanning more than 60 rounds of data collection. MCBS has experienced high response rates over its long history, but response rates have recently begun to decline, leading to a steady increase in contact attempts.

This paper is inspired by the efforts of researchers who have worked to define and develop responsive design as a concept and an applied practice (see Groves and Heeringa 2006, Lepkowski et al. 2010, and Mitchell 2012). The analysis uses paradata and rich data related to MCBS late responders in an attempt to identify optimal contact attempt thresholds in future rounds. The results show how reducing contact attempts lowers resource utilization and survey costs but has a mixed effect on the precision of key survey estimates. The results also offer a more refined blueprint for adjusting attempt and conversion efforts on other longitudinal studies.