Online Program Home
My Program

Abstract Details

Activity Number: 298 - SPEED: Innovations in Survey Sampling Designs: Administrative Data, Record Linkage, Non-Probability Samples, and More
Type: Contributed
Date/Time: Tuesday, July 31, 2018 : 8:30 AM to 10:20 AM
Sponsor: Survey Research Methods Section
Abstract #328590 Presentation
Title: Bayesian Methods for Stratified Sample Allocation Using Imperfect Information
Author(s): Jonathan Mendelson* and Joe Sedransk
Companies: University of Maryland and University of Maryland
Keywords: Bayesian decision theory; survey sampling; stratified sample allocation; establishment surveys; ratio estimation
Abstract:

For many survey sample designs, there are analytical results indicating the optimal sample allocations, conditional upon knowing certain population characteristics (e.g., strata variances). In practice, such characteristics are typically unknown and may be estimated from previous surveys, after which these estimates may be used in place of knowing the true values in estimating the optimal allocation. However, there is often little attention given to the potential impact of imperfect information about the values of parameters needed to design the sample. We examine stratified sample allocation in the context of establishment surveys, using a Bayesian decision theoretic framework, which can be used for optimal sample allocation with uncertain population information. Although analytical results can be obtained for simple models, computational issues arise for more complicated models. We will review research to date and possible future directions, with focus on analytical objectives, types of applications, and solving computational problems.


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

Back to the full JSM 2018 program