Online Program Home
My Program

Abstract Details

Activity Number: 427 - Contributed Poster Presentations:Government Statistics Section
Type: Contributed
Date/Time: Tuesday, July 31, 2018 : 2:00 PM to 3:50 PM
Sponsor: Government Statistics Section
Abstract #330921
Title: Bayesian Estimation with Shrinking Both Means and Variances in Heteroscedastic Nested Error Regression Models
Author(s): Hiromasa Tamae*
Keywords: small-area estimation; hierarchical Bayesian model; random dispersion; nested error regression model; shrinkage prior

This research concerns small-area estimation in the heteroscedastic nested error re- gression (HNER) model which assumes that the within-area variances are different among areas. This model is useful for analyzing data such that the within-area variation changes from area to area, but direct estimates of the variances based on the within-area data are poor because of small samples sizes for small-areas. An approach to treating the problem is to consider the hierarchical Bayesian model as- suming the prior distributions for the area variances. The resulting Bayes estimator is stable because both means and variances of small areas are shrunken towards stable statistics.

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

Back to the full JSM 2018 program