신뢰성 성장모형에 대한 소프트웨어 신뢰성 메트릭 추정량의 민감도 분석

Sensitivity analysis of software reliability metric estimator for Software Reliability Growth Models

When we estimate the parameters of software reliability models, we usually use maximum liklihood estimator(MLE). But this method is required a large data set. In particular, when we want to estimate it with small observed data such as early stages of testing, we give rise to the non-existence of MLE. Therefore, it is interesting to look into the influence of parameter estimators obtained using MLE. In this paper, we use two non-homogenous poisson process software reliability growth model: delayed S-shaped model and log power model. In this paper, we calculate the sensitivity of estimators about failure intensity function for two SRGMs respectively.