Proof of Han's hypothesis on relations among two-sided M-Bayesian credible limits and corresponding two-sided classical confidence limits

摘要

This paper studies the interval estimation problem of reliability parameters of binomial distribution, in the case of zero-failure data, using the method of two-sided M-Bayesian credible limit. It proves the hypothesis that was provided by Han [1]: two-sided M-Bayesian credible limits is superior to the corresponding two-sided classical confidence limits when estimation reliability derived from binomial distribution in the case of zero-failure data.