一类判别分析问题的Bayes解

Bayesian Procedure in a Class of Classificati on Problem

设有两个总体 G0 和 G1,分别服从参数为λ0 和λ1的指数分布 ,对于待观测的样本 X,给出了相应的判别分析问题的 Bayes停止判决法则 ,其中损失函数包括试验费用和误判损失两部分 ,Bayes停止判决法则由后验概率比的上界和下界所确定 .

Let G 0 and G 1 be two populations having exponential distribution with parameters λ 0 and λ 1(λ 0>λ 1) respectively.For the life data X in an expe riment, a Bayesian solution of the classification problem is given in this paper , where the loss function of the model is the sum of the cost of the experiment time and the loss due to the wrong decision.The Bayesian stopping rule and decision rule a re determined by the upper and lower limits of posterior probability.