Bayesian Sequential Estimation for One-Parameter Exponential Families
研究了单参数指数族的贝叶斯序贯估计问题，给出了贝叶斯估计量和后验期望损失的简洁表达式，并证明了近视停止规则的最优性和渐近最优性。
Abstract The Bayesian sequential estimation problem for one-parameter exponential families is considered using loss related to the Fisher information and linear sampling cost. Tractible expressions for the Bayes estimator and the posterior expected loss are found, and the myopic, or one-step-ahead, stopping rule is defined. Sufficient conditions are given for optimality of the myopic procedure, and the myopic procedure is shown to be asymptotically optimal in all cases considered.