Gompertz software reliability model: Estimation algorithm and empirical validation
Journal of Systems and Software
EM algorithm for discrete software reliability models: a unified parameter estimation method
HASE'04 Proceedings of the Eighth IEEE international conference on High assurance systems engineering
| Hi-index | 0.00 |
This paper focuses on an estimation problem of modelparameters in software reliability modeling. We introducethe EM (expectation-maximization) algorithms for softwarereliability models and compare them with the classical parameterestimation methods. Especially, we extensively developthe EM algorithms for two cases; (i) the time intervaldata of software fault detection are available, (ii) additivesoftware reliability models based on non-homogeneousPoisson processes are used. In numerical examples, wecompare the iterative schemes based on the EM algorithmswith classical methods such as the Newton's method and theFisher's scoring method and show that the EM algorithmsare attractive in terms of convergence property.