|
|
Journal of Korean Society for Quality Management 2009;37(3): 33-. |
| 신뢰성 성장모형에 대한 소프트웨어 신뢰성 메트릭 추정량의 민감도 분석 |
| 김대경 |
| 전북대학교 통계학과 |
| Sensitivity analysis of software reliability metric estimator for Software Reliability Growth Models |
| Dae-Kyung Kim |
| Chonbuk National University, Department of Statistics |
|
|
|
|
|
| ABSTRACT |
|
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. |
| Key Words:
software reliability metric;MLE;SRGM;NHPP;Taylor approximation; |
|
|
|
PDF Links
Full text via DOI 
Download Citation 
