Convergence of dirichlet invariant measures and the limits of bayes estimates
Ram Chandra Tiwari · Communication in Statistics- Theory and Methods · 1988
Using a new constructive definition of the Dirichlet invariant prior measure we study the weak convergence of Dirichlet invariant measures and the limits of the Bayes estimates with respect to squared loss of an estimable parameter of degree k(>1) of the true unknown underlying invariant probability measure as the parameters of the Dirichlet invariant measures are allowed to converge to zero. The asymptotic distribution of the limiting Bayes estimate is derived. This relates to the recent work of Yamato (1986, 1987)