Assessment of C++ object-oriented mutation operators: A selective mutation approach

Mutation testing is an effective but costly testing technique. Several studies have observed that some mutants can be redundant and therefore removed without affecting its effectiveness. Similarly, some mutants may be more effective than others in guiding the tester on the creation of high-quality test cases. Based on these findings, we present an assessment of C++ class mutation operators by classifying them into two rankings: the first ranking sorts the operators based on their degree of redundancy, and the second regarding the quality of the tests they help to design. Both rankings are used in a selective mutation study analysing the trade-off between the reduction achieved and the effectiveness when using a subset of mutants. Experimental results consistently show that leveraging the operators at the top of the two rankings, which are different, lead to a significant reduction in the number of mutants with a minimum loss of effectiveness. Copyright © 0000 John Wiley & Sons, Ltd.