Washington Statistical Society on Meetup

Title: Bayes & Empirical Bayes Benchmarking for Small Area Estimation

  • Presenter: Dr. Malay Ghosh, Department of Statistics, University of Florida
  • Discussant #1: Dr. Gauri Datta, University of Georgia and U.S. Census Bureau
  • Discussant #2: Dr. Brunero Liseo, University of Roma
  • Chair: Ruth Ann Killion, Chief, Demographic Statistical Methods Division, US Census Bureau
  • Date: Wednesday, May 28, 2014
  • Time: 3:00 - 4:15 p.m.
  • Where: Conference Rooms 1&2, US Census Bureau, 4600 Silver Hill Road, Suitland, Maryland
  • Contact: Cynthia Wellons-Hazer, 301-763-4277, Cynthia.L.Wellons.Hazer@census.gov
  • Download the poster

Abstract:

Small area estimation needs explicit or at least implicit use of models in order to borrow information from other similar areas. However, model-based small area estimators face one potential difficulty in that they do not aggregate to the corresponding estimator for a larger geographical area. The talk will discuss some simple Bayesian and empirical Bayesian benchmarking methods, which rectify this problem. Benchmarking methods, in general, are needed to protect against any possible model failure. Very often, they are also used to convince the legislators about the utility of small area estimators.

About the Speakers:

Dr. Malay Ghosh is currently a Distinguished Professor of Statistics at the University of Florida, Gainesville. He represents a true leader in the statistics community in his ability to write influential and profound papers in Bayesian statistics, foundations of statistics and statistical decision theory that have immediate practical applications to many different areas, especially to survey sampling and biostatistics. Professor Ghosh is a Fellow of both the American Statistical Association and the Institute of Mathematical Statistics and an Elected Member of the International Statistical Institute. Furthermore, he has more than 250 refereed publications, co-authored two books and 49 students complete their Ph.D. under his direction. Many of his students have gone on to be successful in both academia and industry. Over the last 40 years, Professor Ghosh's work has been, and continues to be, at the cutting edge of research.

Dr. Gauri Datta is a Professor of Statistics at the University of Georgia and a part-time Mathematical Statistician at the U.S. Census Bureau. His research interests include Bayesian statistics, survey sampling and statistical syndromic surveillance. He has published more than 50 research articles and has coauthored a statistics monograph published by Springer. Professor Datta is a Fellow of both the American Statistical Association and the Institute of Mathematical Statistics and an Elected Member of the International Statistical Institute.

Dr. Brunero Liseo is a Professor of Statistics at University of Rome, La Sapienza. He has published many papers on Bayesian robustness, objective Bayesian analysis, model selection, small area estimation, skew-symmetric distributions, record linkage and Bayesian finite population sampling. He has been actively engaged in research collaboration with ISTAT, the Italian counterpart of the Census Bureau. He is well known for his numerous roles in the Bayesian community and the ISBA.