Formal methods in conformance testing: a probabilistic refinement

Abstract

This paper refines the framework of 'Formal Methods in Conformance Testing' by introducing probabilities for concepts which have a stochastic nature. Test execution is refined into test runs, where each test run is considered as a stochastic process that returns a possible observation with a certain probability. This implies that not every possible observation that could be made, will actually be made. The development process of an implementation from a specification is also viewed as a stochastic process that may result in a specific implementation with a certain probability. Together with a weight assignment on implementations this introduces a valuation measure on implementations. The test run probabilities and the valuation measures are integrated in generalized definitions of soundness and exhaustiveness, which can be used to compare test suites with respect to their ability to accept correct, and to reject erroneous implementations.