Prediction of software failures through logistic regression

The quality of software has been a main concern since the inception of computer software. To be able to produce high quality software, software developers and software testers alike need continuous improvements in their developing and testing methodologies. These improvements should result in better coverage of the input domain, efficient test cases, and in spending fewer testing resources. In this paper we focus on an approach for generating efficient test cases based on the special properties of Design of Experiments and developing a logistic regression model of predicting test case outcomes. Design of Experiments will be utilized to efficiently minimize the number of test cases and the logistic regression model will be used to predict software failures. This approach, in turn, would provide the software tester with a model that reduces the number of test cases, predicts test case outcomes, reduces cost, and allows better forecast of release readiness. We demonstrate our approach using two case studies (TI Interactive software and Microsoft’s Pocket PC operating system). q 2003 Elsevier B.V. All rights reserved.