Improved Estimator of Software Reliability for Weibull Class Models

Abstract

Increase in the usage of software in every field has resulted in having concern over its quality and durability. Research in this area is still of importance and many researchers are still working towards the improvement in the reliability of the software products. Measures of quality in terms of reliability are vast and obtaining the estimate of reliability would provide more insight into the durability and hence in assessing the performance of the software. Software reliability models are widely used in this estimation process. Most of the failure data models fall into Weibull class models, in which, the failures times are assumed to be distributed as Weibull. Herein, such Weibull class software reliability models are considered. It is intended to combine two well-known estimators, viz, the Maximum Likelihood Estimator and the Minimum Variance Unbiased Estimator. Both estimators have their own pros and cons, in terms of the properties satisfied by them. Herein, it is intended to preserve the statistical properties satisfied by both the estimators by combining them to get an Improved Estimator, which satisfies maximum number of statistical properties of a good estimator. In addition, the comparison of the three estimators is carried out by means of coefficient of variation, which considers both the mean and the standard deviation. The comparison is further enhanced by considering the quartile coefficient of dispersion of the three estimators. Some bench mark failure data are considered to establish the efficiency of the improved estimator. © RQD 2023. All rights reserved.All right reserved.