A stopping rule for a compound poisson random variable

Abstract

SUMMARYAn optimal empirical Bayesian stopping rule for the Poisson compounded with the geometric distribution is developed and applied to the problem of the sequential testing of computer software. For each checkpoint in time, either the software satisfies a desired economic criterion, or else the software testing is continued.

The development of a destructive sampling method designed for high quality production processes (DSM-HQ)

“…This model, which is similar to the one used by Dalal and Mallows (1988) as well as Randolph and Sahinoglu (1995), motivates an optimal stopping point for sampling. The break-even point occurs at…”

“…The optimal stopping rule motivated by that of Randolph and Sahinoglu (1995) results in the economical sample size being the smallest n such that y > 0. It is not uncommon that a minimum sample size, n min , will be required by a customer and/or no sample size larger than some limit, n max , will be considered by the producer.…”

On the efficiency of a compound Poisson stopping rule for mixed strategy testing

“…However, many models assume one failure at a time, while it is quite common to cover more than 1 branch at a time. Thus, coverage shows a certain clumping effect [9]. This limits the applicability of some of the reliability gowth models and caused us to consider a Bayesian Stopping Rule that models clumping.…”

Efficient Verification of Behavioral Models Using the Sequential Sampling Technique

“…one input pattern applied to a VHOL model may cause many branches to be covered. Thus, coverage shows a certain dumping effect [7]. This limits the applicability of some of the reliability growth models.…”

“…This limits the applicability of some of the reliability growth models. An example of a stopping rule that considers dumping is the Compound Poisson Software Reliability Model by Sahinoglu et al, both the time-failure [7] and the dustered (interval) failure models [8]. Oalal et al…”