| |
| Many existing software reliability models are based on the assumption of statistical independence among successive software failures. In reality, this assumption could be easily violated. In recent years, efforts have been made to relax this unrealistic assumption and a software reliability modeling framework considering failure correlation was developed by Goseva-Popstojanova and Trivedi. However, some important issues that are crucial for the proposed models to be used in practice remain unstudied, such as the method of estimation of model parameters. In this paper, we study the parameter estimation problem for this software reliability modeling framework. We propose a relationship function among model parameters which could be essential to the reduction of the number of parameters to be estimated as well as to the reliability prediction using the proposed modeling framework. Two parameter estimation methods have been developed based on deferent types of data available, using Maximum Likelihood Estimation (MLE) method. Simulation results preliminarily show that the accuracy of both proposed estimation methods are satisfactory. |
|
| Keywords:Software Reliability, Failure Correlation, Maximum Likelihood, Parameter Estimation, Markov Renewal Process |
|
