2020-09-26T15:22:52Zhttps://repository.dl.itc.u-tokyo.ac.jp/?action=repository_oaipmhoai:repository.dl.itc.u-tokyo.ac.jp:000427502020-09-08T01:26:09Z00062:07433:0743400009:07435:07436
Characterization of Priors in the Stein ProblemengAdmissibilitydecision theoryestimationgeneralized Bayes estimatorinverse Laplace transformJames-Stein estimatorminimaxityrisk functionshrinkage estimationStein problemuniform dominationhttp://hdl.handle.net/2261/2684Technical ReportKubokawa, TatsuyaThe so-called Stein problem is addressed in the estimation of a mean vector of a multivariate normal distribution with a known covariance matrix. For general prior distributions with sphericity, the paper derives conditions on priors under which the resulting generalized Bayes estimators are minimax. It is also shown that the conditions can be expressed based on the inverse Laplace transform of the general prior. The relationsip between Stein's super-harmonic condition and the general conditions is discussed. Finally, a characterization of the priors for the admissibility is given, and admissible and minimax estimators are developed.Revised in June 2006; subsequently published in Journal of the Japan Statistical Society (2007), 37, 207-237.本文フィルはリンク先を参照のことDiscussion paper series. CIRJE-FCIRJE-F-4092006-03AA11450569application/pdf330日本経済国際共同センターhttp://www.cirje.e.u-tokyo.ac.jp/research/dp/2006/2006cf409ab.html2017-06-16