Title :
Measure what counts: An evaluation pattern for software data analysis
Author :
Letier, Emmanuel ; Fitzgerald, Conor
Author_Institution :
Dept. of Comput. Sci., Univ. Coll. London, London, UK
Abstract :
The `Measure what counts´ pattern consists in evaluating software data analysis techniques against problem-specific measures related to cost and other stakeholders´ goals instead of relying solely on generic metrics such as recall, precision, F-measure, and Receiver Operating Characteristic area.
Keywords :
data analysis; measure what counts evaluation pattern; problem-specific measures; software data analysis techniques; Analytical models; Context; Data analysis; Data models; Mathematical model; Software; Software engineering;
Conference_Titel :
Data Analysis Patterns in Software Engineering (DAPSE), 2013 1st International Workshop on
Conference_Location :
San Francisco, CA
DOI :
10.1109/DAPSE.2013.6603804
