Enhancing evaluation techniques using Mutation Operator Production Rule System and accidental fault methodology

Doctor of PhilosophyDepartment of Computing and Information SciencesDavid A. GustafsonSoftware testing is an essential component of software development life cycle, and certain software testing methodologies require enormous amounts of time and expense in order to detect and correct errors in a software system. The two primary goals of any testing methodology are error detection and increased reliability. Each methodology utilizes a unique technique to achieve these goals and detect faults in the software. In this paper, an evaluation approach is presented that can enhance evaluation techniques for software testing methodologies. Firstly, a new framework, Mutation Operator Production Rule System (MOPRS), is introduced that allows specifications of mutation operators that can be effective, precise, and focused on object-oriented faults. A new concept of effective mutation operator has been added to this system. An effective mutation operator is a precise set of rules that when applied to a program creates a set of mutants, which when killed by a test suite, will mean that further seeded or accidental faults characterized by the same fault type are highly likely to be killed by the same test suite. These effective mutation operators focus on fault types specific to object-oriented programming concepts. As a result, object-oriented faults are detected instead of finding traditional faults common to non-object-oriented and object-oriented programming. These mutation operators cover the gaps in the existing set of mutation operators. An evaluation method is described that can enhance the evaluation techniques, Accidental Fault Methodology (AFM), for software testing methodologies. When effective mutation operators are used along with this evaluation technique, it will demonstrate if the software testing methodology successfully detected induced faults and also any accidental faults specific to the object-oriented fault type