Online Program Home
My Program

Abstract Details

Activity Number: 335 - SRMS/SSS/GSS Student Paper Competition
Type: Topic Contributed
Date/Time: Tuesday, July 30, 2019 : 10:30 AM to 12:20 PM
Sponsor: Social Statistics Section
Abstract #303057 Presentation
Title: Predicting Interviewer Effects Using Paradata
Author(s): Sharan Sharma* and Michael Elliott
Companies: University of Michigan and University of Michigan
Keywords: Interviewer effects; Paradata; Survey quality control

Consideration of interviewer effects (interviewer measurement error variance) in active quality control does not seem widespread despite its known effect on reducing precision of survey estimates. We address this issue by exploring the use of paradata (keystroke and time stamp data) as proxies of interviewer effects. We first estimate interviewer effects for each item in our analysis. We then compute proportions of variance explained by interviewer-level paradata inputs. These inputs are selected from a pool of paradata measures using adaptive lasso. Realistic predictions of the proportions of explained variance are computed using a bootstrap-based method. We find promising results; paradata explain more than half the magnitude of interviewer effects on average across items, outperforming other interviewer-level variables. While the focus in the literature and in practice has been on time-based paradata (e.g., item times) non-time based paradata (e.g., item revisits) generally outperform the former. We discuss how survey organizations can use these findings in active quality control. Our analyses use data from the 2015 wave of the Panel Study of Income Dynamics(PSID).

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program