|
Activity Number:
|
207
- Survey Mode Research
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 8, 2022 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Survey Research Methods Section
|
|
Abstract #322972
|
|
|
Title:
|
Evaluating Methods to Adjust for Mode Effects in a Longitudinal Study
|
|
Author(s):
|
Xiaoshu Zhu* and Ting Yan
|
|
Companies:
|
Westat and Westat
|
|
Keywords:
|
Mode effects;
Regression-based methods;
Propensity score weighting;
Multiple imputation;
Longitudinal study
|
|
Abstract:
|
Surveys are increasingly using multiple modes of data collection to recruit and to interview sampled persons. Multimode surveys have the advantages of improving response rates while maintaining cost. A mode effect occurs when estimates differ across modes used in a multimode design. Mode effects are a major concern in mixed mode surveys and research is needed to evaluate approaches to statistically adjust for them. This paper evaluates the performance of three statistical adjustment approaches. The first approach is to regress survey outcomes on mode and other relevant variables. The second approach is to weight respondents by propensity scores to adjust for mode effect. The third approach is to treat mode effect as missing data problem and to impute response in a different mode. A synthetic dataset generated from a longitudinal survey is utilized for evaluation. Longitudinal surveys provide rich information on survey outcomes and auxiliary variables over time, all of which can be utilized to improve estimates and adjustment of mode effect. This study paper intends to compare the performance of adjustment in two age groups, young adults (18-25 years old) and adults (26 years).
|
Authors who are presenting talks have a * after their name.
