|
Activity Number:
|
549
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 3, 2016 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Survey Research Methods Section
|
|
Abstract #320027
|
View Presentation
|
|
Title:
|
Multiple Imputation for Survey Integration Under Informative Sampling
|
|
Author(s):
|
Seho Park* and Jae-kwang Kim
|
|
Companies:
|
Iowa State University and Iowa State University
|
|
Keywords:
|
calibrated Bayesian method ;
two-phase sample ;
complex sampling design ;
design-consistent estimation
|
|
Abstract:
|
Combining information from two independent surveys is considered. We consider the calibrated Bayesian method that has nice features of Bayesian method and also provides design-consistent estimation. This method is particularly useful in combining two survey samples; we consider not only nested two-phase samples where the second-phase sample is a subsample of the first phase but also non-nested two-phase samples where two independent samples are obtained from the same population. The proposed method can be extended to the case when the two samples are obtained under complex sampling design. We provide a simulation study to demonstrate the performance of the proposed method.
|
Authors who are presenting talks have a * after their name.
