Error Sources and Quality Management in 3MC Surveys

• Activity Number: 13 - Multinational, Multiregional, and Multicultural Surveys (3MC): a Burgeoning Sub-Discipline in Survey Research Methods
• Type: Invited
• Date/Time: Sunday, July 28, 2019 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Zeina Mneimneh* and Julie de Jong and Kristen Cibelli Hibben
• Companies: University of Michigan, Survey Research Center and University of Michigan and University of Michigan
• Keywords: comparative surveys; Total Survey Error; 3MC; interviewer error; cross-cultural; data quality

Abstract

Surveys in multinational, multiregional, and multicultural contexts (“3MC” surveys), designed to achieve comparability across more than one population, are far more complex and face greater sources of error than single-population surveys. Drawing on the Total Survey Error (TSE) framework, increasingly applied to 3MC surveys, we highlight error sources that are unique to or may be more prominent in 3MC surveys. These include errors from additional operations such as translation and adaptation of questions. We also discuss how errors could be magnified in 3MC studies because the nature and size of errors could vary across nations or cultures, thereby threatening comparability. We then explore further and more specifically interviewer error due to its unique importance in 3MC surveys, where interviewer monitoring and interviewer characteristics could vary greatly from one culture to another. We conclude with discussion of current and future approaches to minimizing this and other important sources of error and quality management in 3MC surveys.