Are Bayes Rules Consistent in Information
暂无分享,去创建一个
Bayes’ rule provides a method for constructing estimators of probability density functions in both parametric and nonparametric cases. Let X 1, X 2, ..., X n be a random sample from an unknown probability measure P 0 with density function p 0(x) with respect to a dominating measure λ(dx). Let µ be a prior probability measure on the space of all probability measures P which have densities p(x) = dP/dλ. Then the mean of the posterior yields the following estimator of the density function
$${{\hat{p}}_{n}}(x) = \hat{p}(x;{{X}_{1}},{{X}_{2}}, \ldots ,{{X}_{n}}) = \frac{{\smallint p(x)(\prod _{{i = 1}}^{n}p({{X}_{i}}))d\mu }}{{\smallint (\prod _{{i = 1}}^{n}p({{X}_{i}}))d\mu }}.$$
[1] D. Freedman. On the Asymptotic Behavior of Bayes' Estimates in the Discrete Case , 1963 .
[2] L. Schwartz. On Bayes procedures , 1965 .
[3] H. Strasser. Consistency of Maximum Likelihood and Bayes Estimates , 1981 .
[4] Discussion: On the Consistency of Bayes Estimates , 1986 .