New Measures for Assessing Non-Ignorable Selection Bias in Non-Probability Samples and Low Response Rate Probability Samples

• Activity Number: 105 - Advances in Statistical Methods and Models for Real-Time Surveys
• Type: Topic Contributed
• Date/Time: Monday, August 8, 2022 : 8:30 AM to 10:20 AM
• Sponsor: Survey Research Methods Section
• Author(s): Brady Thomas West*
• Companies: Institute for Social Research, University of Michigan-Ann Arbor
• Keywords: Selection Bias; Non-Ignorable Nonresponse; Non-Probability Sampling; Responsive Survey Design; Nonresponse Adjustment

Abstract

Recent developments in survey statistics have yielded simple, novel measures of the non-ignorable selection bias in estimates of means, proportions, and regression coefficients that may arise due to deviations from ignorable sample selection, where these deviations might be introduced by the sampling mechanism (e.g., non-probability sampling) or survey nonresponse. Responsive survey designs rely on active monitoring of sound indicators of survey errors to inform real-time design decisions, and these new measures, which are easy to compute at any point in time during a data collection, have the potential to serve as useful indicators of the possible selection bias in estimates of interest. This presentation will review the computation of these indicators, the data required to compute them, software tools for computing them, and how they might be actively monitored in real time to inform design decisions in responsive survey designs.