The Comparative Study of NHPP Half-Logistic Distribution Software Reliability Model using the Perspective of Learning Effects

In this study, software products developed in the course of testing, software managers in the process of testing software test and test tools for effective learning effects perspective have been studied using the NHPP software reliability models. The finite failure non-homogeneous Poisson process models presented and want to use half-logistic distribution as the lifetime distribution which used to statistical process. Software error detection techniques known in advance, but influencing factors for considering the autonomous errors-detected factor and learning factors ,by prior experience, to find precisely the error factor setting up the testing manager is presented on comparing the problem. The general result, case of the learning factor is greater than automatic error is efficient model, but, when applied to halfLogistic distribution model, case of autonomous errors-detected factor greater learning factor is efficient. This paper, a failure data analysis of applying using time between failures and parameter estimation using maximum likelihood estimation method were made, after the efficiency of the data through trend analysis, model selection was performed using the mean square error and coefficient of determination.