New Directions for Extending Research on Interviewer Effects in Surveys

June 12, 2017, 1pm

GESIS, Mannheim, B2,8

Brady T. West

Abstract

This presentation will provide an overview of some recent, ongoing, and proposed research on the effects that interviewers can have on the quality of both survey data and survey paradata (and survey estimates based on those data). Specifically, four research questions that have received only minimal attention in the literature to date will be addressed or introduced:

1.      What is the relative decomposition of interviewer variance in a variety of survey variables in terms of sampling error variance, nonresponse error variance, and measurement error variance among interviewers, and how can we study these decompositions in the absence of interpenetrated sample designs?

2.      What effects can interviewers have on the quality of survey paradata, such as interviewer observations, records of call attempts, or post-survey observations, and what design or training strategies can be used to reduce these effects?

3.      Do interviewer observations add predictive power in panel surveys, above and beyond key survey measures collected at previous waves?

4.      How do interviewers affect the quality of estimated regression coefficients?

Findings from recent peer-reviewed studies will be discussed with respect to the first question, along with implications for the fourth question based on these findings. Recent findings from studies by the presenter and his colleagues will also be reviewed with respect to the second question, and proposed research in this area will be discussed. Findings from the PASS study will be reviewed with respect to the third question, where evidence suggests that interviewer observations of income and receipt of unemployment benefits in an economic panel survey in Germany do in fact add predictive power to models for current-wave variables. Finally, a proposal is currently under development to examine the fourth research question, and an initial simulation study motivating this work will be reviewed. 

About the speaker

Brady T. West is a Research Associate Professor in the Survey Methodology Program, located within the Survey Research Center at the Institute for Social Research on the University of Michigan-Ann Arbor (U-M) campus. He also serves as a Statistical Consultant on the U-M Consulting for Statistics, Computing, and Analytics Research (CSCAR) team. He earned his PhD from the Michigan Program in Survey Methodology in 2011. Before that, he received an MA in Applied Statistics from the U-M Statistics Department in 2002, being recognized as an Outstanding First-year Applied Masters student, and a BS in Statistics with Highest Honors and Highest Distinction from the U-M Statistics Department in 2001. His current research interests include the implications of measurement error in auxiliary variables and survey paradata for survey estimation, survey nonresponse, interviewer variance, and multilevel regression models for clustered and longitudinal data. He is the lead author of a book comparing different statistical software packages in terms of their mixed-effects modeling procedures (Linear Mixed Models: A Practical Guide using Statistical Software, Second Edition, Chapman Hall/CRC Press, 2014), and he is a co-author of a second book entitled Applied Survey Data Analysis (with Steven Heeringa and Pat Berglund), which was published by Chapman Hall in April 2010 and has a second edition in press that will be available in mid-2017. Brady lives in Dexter, Michigan with his wife Laura, his son Carter, his daughter Everleigh, and his American Cocker Spaniel Bailey.