The aim of the work described in this thesis was to improve NCR's decision making process for progressing software products through the development cycle. The first chapter briefly describes the software development process at NCR, detailing documentation review and software testing techniques. The objectives and reasons for investigating software reliability models as a tool in the decision making process are outlined. There follows a short review of software reliability models, with the Littlewood and Verrall Bayesian model considered in detail. The difficulties in using this model to obtain estimates for model parameters and time to next failure are described. These estimation difficulties exist using the model on good datasets, in this case simulated failure data, and the difficulties are compounded when used with real failure data. The problems of collecting and recording failure data are outlined, highlighting the inadequacies of these collected data, and real failure data are analysed. Software reliability models are used in an attempt to quantify the reliability of real software products. The thesis concludes by summarising the problems encountered when using reliability models to measure software products and suggests future research into metrics that are required in this area of software engineering.
|Date of Award||May 1990|