UNIVERSITY OF HERTFORDSHIRE
      COMPUTER SCIENCE RESEARCH COLLOQUIUM


    "The Misuse of the NASA Metrics Data
        for Software Defect Prediction"

                David Gray
  (Computer Science, University of Hertfordshire)


         2 November 2011 (Wednesday)
             Meeting Room C152

         Hatfield, College Lane Campus
                 1-2  pm

         Everyone is Welcome to Attend

         Refreshments will be available

Abstract:

The NASA Metrics Data Program data sets have been heavily used in software
defect prediction experiments. In this talk I will demonstrate and explain
why these data sets require significant pre-processing in order to be
suitable for defect prediction. This involves a thorough data cleansing
process, where between 6 to 90 percent of data points are removed from
each set. The issues found in these data sets potentially jeopardise
much prior research, and reiterate that data quality is a serious issue
in software engineering.

--
http://cs-colloq.feis.herts.ac.uk/