Case Studies on Monitoring Interviewer Behavior in Cross-National and International Surveys

• Activity Number: 679
• Type: Topic Contributed
• Date/Time: Thursday, August 13, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Social Statistics Section
• Author(s): Sharan Sharma* and Lars Lyberg and Zeina Mneimneh
• Companies: University of Michigan and Stockholm University and University of Michigan
• Keywords: quality control ; interviewer monitoring ; cross-cultural surveys ; paradata ; international surveys

Abstract

Quality control is needed during all the phases of a survey lifecycle. Surveys implemented in diverse cultures are no exception; the diversity of space, time, infrastructure, and expertise makes quality control critical. Many cross-cultural surveys are interviewer-administered and are conducted in less than ideal circumstances where interviewing traditions differ, multiple contractors are hired to implement the work and interviewer workloads vary greatly. Under such conditions, interviewers become an important source of survey error (variance/bias), and close monitoring becomes essential. This presentation addresses interviewers as an important source of error in surveys conducted in diverse cultures. It discusses some of the cutting-edge methods that have been implemented to monitor interviewer behavior and reduce interviewer error in a number of surveys including two panel surveys in India, a national mental health survey in the Kingdom of Saudi Arabia, a cross-cultural attitudinal survey and the European Social Survey. The presentation concludes with a discussion on future directions on quality assurance and control in diverse cultures.