期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：6
出版社：S.S. Mishra
摘要：In this Research Paper the experimental study of WCS and WChS metrics performed in detail by evaluating with other regularly mentioned methods. CBO, LCOM and RFC are used for evaluating. This article also shows an experimental methodology of importance of Weighted Coupling Support (WCS) and Weighted Cohesion Support (WChS) also with design metrics like Response for a Class (RFC), Coupling Between Object classes (CBO), Number of Children (NOC), Depth of Inheritance Tree (DIT), Lack of Cohesion Between Methods (LCOM), Weighted Methods per Class (WMC) in defect prediction models. Several releases of various open-source projects were checked upon. Each metrics was checked upon with the Pearson correlation coefficients with amount of defects. Later defect prediction models were developed making use of linear stepwise regression and discriminatory analysis was performed. As the stepwise regression was made use, the acquire models always had a subset of the investigated
关键词：Empirical Analysis; WCS; WChS; Logistic Regression; Linear Regression
