We consider the estimation of Σ of the p-dimensional normal distribution Np(0,Σ) under the restriction where the eigenvalues of Σ have an upper or lower bound. From adecision-theoretic point of view, we evaluate the performance of the REML (restricted maximum likelihood estimator) with Stein′s loss function and propose another estimator that dominates the REML.
Print ISSN: 0721-2631
Volume: 21, 04/2003
Pages: 327