|
Organizers |
Estimating Quantiles of Normal Populations
by
Somesh Kumar
Dept. of Mathematics, IIT Kharagpur
Coauthors: Manas Ranjan Tripathy
Let X = (X1, X2, …, Xm) and Y = (Y1, Y2, …, Yn) be independent random samples from normal populations with a common mean and possibly different variances. The parameters are all unknown and we are interested in estimating the quantile of the first population with respect to a quadratic loss function. We establish the minimaxity of the best affine equivariant estimator based on the first sample. A general inadmissibility result for affine equivariant estimators is proved. A numerical comparison of the risk functions for various estimators of the quantile is made. These results have been generalized to the case of bivariate normal population also.
Date received: January 23, 2007
Copyright © 2007 by the author(s). The author(s) of this document and the organizers of the conference have granted their consent to include this abstract in Atlas Conferences Inc. Document # cata-45.