Software Measurement Programs: Evaluations and Solutions

Abstract

Every software development process either generates or uses measurement data that is essential to understand, evaluate, improve and predict the software processes, products, and resources. Software development organizations implement measurement programs (MPs) as part of their measurement processes. However, implementing successful MPs still remains a challenge. The aim of this thesis is to comprehensively evaluate and then contribute towards planning and implementation issues of MPs. This research is conducted in three phases: 1) problem identification 2) solution design and 3) industrial evaluation of solutions. A mix of qualitative and quantitative research methods is used appropriately for each phase. In the first phase, comprehensive literature reviews of the studies on MPs are conducted to enable a better understanding of the existing measurement planning models, tools, challenges, success factors, and metrics selection methods of implementing MPs in general and specifically for small and medium enterprises (SMEs). In addition, challenges of implementing MPs in large organizations and SMEs are analyzed. In the second phase, multiple solutions are proposed to improve the planning of MPs. The solutions are based on the analysis of research gaps involving the challenges and success factors of implementing MPs. First, a set of key components of MPs is identified for planning a MP. Second, a model of success factors for planning MPs in general is proposed. Third, a model of success factors for planning MPs specifically in SMEs is proposed. Fourth, a model called data-driven measurement for software prediction (D2MSP) is proposed to overcome the challenge of using already collected measurement data for prediction of software attributes e.g., defects. In the third phase, the solutions are evaluated in the software development industry with the help of surveys and empirical data of software projects. A set of key components and a model of success factors are evaluated based on a survey among 200 software professionals working in the Pakistani software development industry. A model of success for planning MPs specifically in SMEs is evaluated based on a survey among 217 software professionals working in SMEs of Pakistan. The D2MSP xi model is evaluated using a dataset of 760 projects and later applied in a software development organization as a case study. Overall, this research contributes to the theory and practice of software measurement by providing an improved understanding of planning software MPs and proposing and validating models of success factors and the D 2MSP model for planning MPs.