Online Program Home
My Program

Abstract Details

Activity Number: 314 - SPEED: Missing Survey Data: Analysis, Imputation, Design, and Prevention
Type: Contributed
Date/Time: Tuesday, July 31, 2018 : 9:25 AM to 10:10 AM
Sponsor: Survey Research Methods Section
Abstract #332729
Title: Estimating Survey Attrition Phases Using Change-Point Models
Author(s): Camille Hochheimer* and Roy T Sabo and Alex H Krist
Companies: Virginia Commonwealth University and Virginia Commonwealth University and Virginia Commonwealth University
Keywords: attrition; dropout; survey; questionnaire; change-point hazard
Abstract:

As web-based surveys become an increasingly popular mode of data collection, the ease of dropping out in the online setting is a growing issue in ensuring data quality. One theory is that dropout or attrition occurs in phases that can be generalized to phases of high dropout and phases of stable use. To estimate the location of these phase transitions we use change-point hazard models with survey dropout as a time-to-event outcome. Specifically, we investigate a test for a piecewise constant hazard model and compare it to an extension of a Weibull change-point hazard model through a simulation study and application to survey data on patient cancer screening preferences. Using both methods, we test the null hypothesis of no phases of attrition (no change-points) against the alternative hypothesis that distinct attrition phases exist (at least one change-point). Extensions of these models to account for covariates are also discussed.


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

Back to the full JSM 2018 program