Comparison of MCMC and ADM methods for Hierarchical Bayesian Estimates in Small Area Estimation


Poster Session

Poster no.12

Author: Ying Han (Mathematics Department, University of Maryland, College Park)

In this paper, we compare the accuracy of the Monte Carlo Markov Chain (MCMC) and Adjusted Density Method (ADM) in approximating Hierarchical Bayesian (HB) estimates in the context of small area estimation. We apply a three-level hierarchical model to poverty data from the 2005 American Community Survey and experiment with a flat improper prior. Both MCMC and ADM are used to estimate the poverty rates for the 0-17 year old children in 775 counties of America. Figures and Tables are displayed to evaluate their performance. Our results indicate that there is little difference in accuracy between the two methods but ADM method is much faster than MCMC.

Keywords: Monte Carlo Markov Chain; Adjusted Density Method; Hierarchical Model; Poverty Rate.