ON MEASURES OF UNCERTAINTY OF EMPIRICAL BAYES SMALL-AREA ESTIMATORS

Partha Lahiri

University of Nebraska-Lincoln

Refreshments: 3:30 - 4:00 p.m. Monday, November 1, at 327 Yost
Talk: 4:00 - 5:00 p.m. Monday, November 1, at 327 Yost.

Small-area typically refers to a small geographic area or a demographic group for which very little information is obtained from the sample surveys. An empirical Bayes method uses sample survey data in conjunction with relevant supplementary data which are obtained from various administrative sources. The method has been found to be very useful in many applications of small-area estimation and related problems.

A method based on bootstrap samples is proposed to measure the accuracy of the proposed empirical Bayes estimator of a small-area characteristic. A simple approximation of the method which does not require any bootstrap simulation is also proposed. The model expectation of the proposed measure of uncertainty of the empirical Bayes (EB) estimator is equal to the integrated Bayes risk of the EB estimator up to the order $o(m^{-1}),$ where $m$ denotes the number of small-areas. It is interesting to note that for a special case of our model, the measure is identical, up to the order $o(m^{-1})$, with a measure of uncertainty previously proposed by Morris (1983). Since Morris' measure is an approximation to a hierarchical Bayes posterior variance, the proposed method enjoys both desirable frequentist and hierarchical Bayes properties. Two well-known data sets are considered to compare the proposed method with some existing methods. A Monte Carlo simulation is conducted to compare the performances of different measures of uncertainty.

(This is a joint work with Ferry Butar Butar, Sam Houston State University)

Questions? Nidhan Choudhuri