arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1301.0569cs.AI
收藏

无先验概率的似然信息统计决策

Statistical Decisions Using Likelihood Information Without Prior Probabilities

University of Kansas School of Business(堪萨斯大学商学院)

Phan H. Giang, Prakash P. Shenoy

摘要:

本文提出了一种决策理论的方法来统计推断,满足似然原理(LP),而不使用先验信息。与也满足LP的贝叶斯方法不同,我们不假设未知参数的先验分布的知识。对于从实验中得到的信息,我们的解比Wald的极大极小解更有效,但是对于实验前已知的信息,我们的解比贝叶斯解需要更少的输入。

英文摘要:

This paper presents a decision-theoretic approach to statistical inference that satisfies the likelihood principle (LP) without using prior information. Unlike the Bayesian approach, which also satisfies LP, we do not assume knowledge of the prior distribution of the unknown parameter. With respect to information that can be obtained from an experiment, our solution is more efficient than Wald's minimax solution.However, with respect to information assumed to be known before the experiment, our solution demands less input than the Bayesian solution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑