Cramer-Rao type integral inequalities for estimators of functions of multidimensional parameter

Prakasa Rao, B. L. S. (1992) Cramer-Rao type integral inequalities for estimators of functions of multidimensional parameter Sankhya - Series A, 54 (1). pp. 53-73. ISSN 0581-572X

Full text not available from this repository.

Official URL: http://www.jstor.org/pss/25050858

Abstract

Cramer-Rao type integral inequalities for the integrated risk for estimators of functions of multidimensional parameter are derived extending the work of Borovkov (1984). As an application, a lower bound for the local asymptotic minimax risk of an estimator is obtained when the components of the parameter are orthogonal. Several examples are presented illustrating the results. The problem of estimation of function of mean vector and covariance matrix of a multivariate normal distribution is discussed.

Item Type:Article
Source:Copyright of this article belongs to Indian Statistical Institute.
ID Code:37252
Deposited On:26 Apr 2011 10:48
Last Modified:26 Apr 2011 10:48

Repository Staff Only: item control page