Bayesian hierarchical models are effective tools for small area estimation by pooling small datasets together. The pooling procedures allow individual areas to ”borrow strength” from each other to desirably improve the estimation. This work is an extension of Nandram and Choi (2002), NC, to perform inference on finite population proportions when there exists non-identifiability of the missing pattern for nonresponse in binary survey data. We review the small-area selection model (SSM) in NC which is able to incorporate non-identifiability. Moreover, the proposed SSM, individual-area selection model (ISM), and small-area pattern- mixture model (SPM) are evaluated by real crime data in Stasny (1991). Furthermore, the methodology is compared to ISM and SPM using simulated small area datasets. Computational issues related to the MCMC are also explained.

Creator

• Liu, Shiao

Colaboradores

• Nandram, Balgobin

Degree

• MS

Unit

• Mathematical Sciences

Publisher

• Worcester Polytechnic Institute

Language

• English

Identifier

• etd-042618-062820

Palabra Clave

• MCMC
• Small Area Estimation
• Bayesian Hierarchical Models
• Nonresponse

Advisor

• Nandram, Balgobin

Defense date

• 2018-04-26

Year

• 2018

Date created

• 2018-04-26

Resource type

• Thesis

Rights statement

• In Copyright