A New Family of Prior Distributions for Attribute Reliability Growth

摘要

This paper introduces a new class of prior distributions for reliability growth tests with binomial data under the monotone model. The expressions of corresponding means and variances for all stages with and without conditioning are obtained. The posterior density and the Bayesian lower bound of the reliability at the end of the test, and a computation method of them is given. The new family of prior distributions includes the uniform prior and the ordered Dirichlet priors presented as special cases. The limitations of the later two are discussed.