Abstract: Approaches for fault localization based on test suites are now collectively called TBFL (testing based fault localization)．However,current algorithms have not taken advantage of the prior knowledge about test cases and program so that they waste these valuable “resources”．[12] introduces a new kind of stochastic TBFL approach whose spirit is to combine the prior knowledge with actual testing activities under stochastic theory,so as to locate program faults．This algorithm presented in [12] may be regarded as a general patter of this kind of approach,from which people can develop various algorithms．Based on the mind of [13],we performed an improvement of the algorithm in [12]．We mainly constructed two tools-the executive matrix E and the efficient matrix F-from the testing results．Then combined with the prior knowledge of test suite and program,the probability of statement being faulty is rated from two scales．Finally the two scales are “averaged”．In this way we got the average rank of program statements about their probability of being faulty,which may help programmers correct program faults．Moreover,this paper presented two standards for comparing different TBFL approaches.And from the investigation of the two standards on some specific instances,the results of the approach presented in this paper are satisfactory.

Key words: Fault localization,Testing based fault localization,Random testing based fault localization