An Alternative Approach for Dealing with Inaccessible Sampled Persons in Registry-Based Samples

• Activity Number: 540
• Type: Contributed
• Date/Time: Wednesday, August 7, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Valerie Hsu*+ and Leyla Mohadjer and Tom Krenzke
• Companies: Westat and Westat and Westat
• Keywords: population registry ; noncoverage ; frame deficiency ; sample design

Abstract

Many participating countries in the first round of the Programme for the International Assessment of Adult Competencies (PIAAC) utilized their national population registries as sampling frames. A list of residents is an ideal frame for PIAAC if it provides adequate coverage and includes reliable information to sample and locate individuals for the interview. One challenge faced by some countries with registry samples is the inability to locate some of the selected persons at the registered address, due to erroneous registry data, resulting in high nonresponse rates. For countries with a high proportion of inaccessible persons, we developed an alternative approach that employs address-based sampling in conjunction with person-based sampling from a registry. This paper describes the multi-frame design and discusses the advantages of such a design as compared to single-frame designs that employ person-level sampling from registries.