Online Program Home
My Program

Abstract Details

Activity Number: 450 - Inference with Clustered Data: Lessons from Multiple Disciplines
Type: Invited
Date/Time: Wednesday, August 1, 2018 : 8:30 AM to 10:20 AM
Sponsor: Survey Research Methods Section
Abstract #326488
Title: Pseudo-Population Bootstrap Procedures for Multi-Stage Sampling Designs
Author(s): Sixia Chen* and David Haziza
Companies: University of Oklahoma and Université de Montréal
Keywords: variance estimation; high entropy sampling designs; quantiles; unit nonresponse

Inference with clustered survey data is important since multi-stage designs are often used to save time and costs. Variance estimation in the presence of multi-stage sampling is challenging. We consider pseudo-population bootstrap procedures. In the context of complete data, Chauvet (2007) proposed a p pseudo-population procedure and established its properties for smooth functions of means. In this presentation, we discuss pseudo-population bootstrap procedures with general clustered survey data. The proposed method can also be used in the presence of weight adjustment for unit nonresponse, imputation and weight trimming. Theoretical properties of bootstrap variance estimators will be discussed. Results from a limited simulation study, comparing the proposed approach with some existing ones, will be presented.

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

Back to the full JSM 2018 program