Filters








2 Hits in 14.5 sec

Problems with Precision: A Response to "Comments on 'Data Mining Static Code Attributes to Learn Defect Predictors'"

Tim Menzies, Alex Dekhtyar, Justin Distefano, Jeremy Greenwald
2007 IEEE Transactions on Software Engineering  
Hence, if detectors were to be assessed in terms of precision, it would be very difficult to show that method A was better than B. Another problem with precision instability is maintainability.  ...  We have a different view, for two reasons. First, for SE data sets with large neg=pos ratios, it is often required to lower precision to achieve higher recall.  ... 
doi:10.1109/tse.2007.70721 fatcat:zjrqsqtmunc6lj55wxropx5hja

Software Defect Prediction Using Static Code Metrics: Formulating a Methodology [article]

David Philip Harry Gray, UH Research Archive, UH Research Archive
2013
The aim of the methodology is to be able to obtain a realistic estimate of potential real-world predictive performance, and also to have simple performance baselines with which to compare against the actual  ...  The redundant, or repeated data points are shown to be the cause of potentially serious data mining problems.  ...  Problems with Precision: A Response to "Comments on 'Data Mining Static Code Attributes to Learn Defect Predictors" '. IEEE Transactions on Software Engineering, vol. 33, pages 637-640, 2007.  ... 
doi:10.18745/th.11067 fatcat:gvwyfsonojdexpzakxgglhtxqe