Dynamic Reliability Models for Software Using Time-Dependent Covariates

This article presents a new model for software reliability characterization using a growth curve formulation that allows model parameters to vary as a function of covariate information. In the software reliability framework, covariates may include such things as the number of lines of code for a product throughout its development cycle and the number of customer licenses sold over the field life of a product. We describe a Bayesian framework for inference and model assessment, using Markov chain Monte Carlo techniques, that allows for incorporation of subjective information about the parameters through the assumed prior distributions. The methods are illustrated using simulated defect data and defect data collected during development for two large commercial software products.