An Improved Confounding Effect Model for Software Defect Prediction
Open Access
- 8 March 2023
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 13 (6) , 3459
Abstract
Software defect prediction technology can effectively improve software quality. Depending on the code metrics, machine learning models are built to predict potential defects. Some researchers have indicated that the size metric could cause confounding effects and bias the prediction results. However, evidence shows that the real confounder should be the development cycle and number of developers, which could bring confounding effects when using code metrics for prediction. This paper proposes an improved confounding effect model, introducing a new confounding variable into the traditional model. On multiple projects, we experimentally analyzed the effect extent of the confounding variable. Furthermore, we verified that controlling confounding variables helps improve the predictive model’s performance.Keywords
Funding Information
- National Social Science Fund of China (21CGJ006)
This publication has 38 references indexed in Scilit:
- Software fault prediction metrics: A systematic literature reviewInformation and Software Technology, 2013
- Software fault prediction: A literature review and current trendsExpert Systems with Applications, 2011
- A systematic review of software fault prediction studiesExpert Systems with Applications, 2009
- The effectiveness of software metrics in identifying error-prone classes in post-release software evolution processJournal of Systems and Software, 2008
- Consistency-based search in feature selectionArtificial Intelligence, 2003
- The confounding effect of class size on the validity of object-oriented metricsIEEE Transactions on Software Engineering, 2001
- The prediction of faulty classes using object-oriented design metricsJournal of Systems and Software, 2001
- A validation of object-oriented design metrics as quality indicatorsIEEE Transactions on Software Engineering, 1996
- Software quality: the elusive target [special issues section]IEEE Software, 1996
- Sample Selection Bias as a Specification ErrorEconometrica, 1979