Bayesian Analysis of the Logarithmic-Poisson Execution Time Model Based on ExpertOpinion and Failure Data

摘要

In this paper, we propose a Bayesian approach for predicting the number offailures in a piece of software, using the logarithmic. Poisson model, a non homogeneous Poisson process (NHPP) commonly used for describing software failures. A similar approach can be applied to other forms of the NHPP. The key feature of our approach is that now we are able to use, in a formal manner expert knowledge on software testing, as for example, published information on the empirical experiences of other researchers. This is accomplished by treating such information as expert opinion in the construction of a likelihood function which leads us to a joint distribution. Our procedure is computationally intensive, but for the case of the logarithmic-Poisson model has been codified for use on a personal computer. We illustrate the working of our approach via some real live data on software testing. We wish to emphasize that our aim is not to propose another model for software reliability assessment. Rather what we have here is a methodology that can be invoked with existing software reliability models.