Empirical Likelihood for Small-Area Estimation

• Activity Number: 86
• Type: Contributed
• Date/Time: Sunday, August 1, 2010 : 4:00 PM to 5:50 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Sanjay Chaudhuri*+ and Malay Ghosh
• Companies: National University of Singapore and University of Florida
• Keywords: Small area Estimation ; Empirical likelihood

Abstract

Current methodologies in small area estimation are mostly either parametric or are heavily dependent on the assumed linearity of the estimators of the small area means. We discuss an alternative empirical likelihood based Bayesian approach. This approach neither requires a parametric likelihood nor needs to assume any linearity of the estimators. Moreover, the proposed method can handle both discrete and continuous data in a unified manner. Empirical likelihood for both area and unit level models are introduced. Performance of our method is illustrated through real datasets.