N. Nagappan, T. Ball, and A. Zeller. International Conference on Software engineering, page 452--461. Shanghai, China, ACM, (September 2006)
Abstract
What is it that makes software fail? In an empirical study of the post-release defect history of five Microsoft software systems, we found that failure-prone software entities are statistically correlated with code complexity measures. However, there is no single set of complexity metrics that could act as a universally best defect predictor. Using principal component analysis on the code metrics, we built regression models that accurately predict the likelihood of post-release defects for new entities. The approach can easily be generalized to arbitrary projects; in particular, predictors obtained from one project can also be significant for new, similar projects.
%0 Conference Paper
%1 nagappan06
%A Nagappan, Nachiappan
%A Ball, Thomas
%A Zeller, Andreas
%B International Conference on Software engineering
%C Shanghai, China
%D 2006
%I ACM
%K imported
%P 452--461
%T Mining metrics to predict component failures
%U http://doi.acm.org/10.1145/1134285.1134349
%X What is it that makes software fail? In an empirical study of the post-release defect history of five Microsoft software systems, we found that failure-prone software entities are statistically correlated with code complexity measures. However, there is no single set of complexity metrics that could act as a universally best defect predictor. Using principal component analysis on the code metrics, we built regression models that accurately predict the likelihood of post-release defects for new entities. The approach can easily be generalized to arbitrary projects; in particular, predictors obtained from one project can also be significant for new, similar projects.
%@ 1-59593-375-1
@inproceedings{nagappan06,
abstract = {What is it that makes software fail? In an empirical study of the post-release defect history of five Microsoft software systems, we found that failure-prone software entities are statistically correlated with code complexity measures. However, there is no single set of complexity metrics that could act as a universally best defect predictor. Using principal component analysis on the code metrics, we built regression models that accurately predict the likelihood of post-release defects for new entities. The approach can easily be generalized to arbitrary projects; in particular, predictors obtained from one project can also be significant for new, similar projects.},
added-at = {2007-11-23T17:50:43.000+0100},
address = {Shanghai, China},
author = {Nagappan, Nachiappan and Ball, Thomas and Zeller, Andreas},
biburl = {https://www.bibsonomy.org/bibtex/237bb9df82b14e322d859d4f180d1c861/neilernst},
booktitle = {International Conference on Software engineering},
description = {Mining metrics to predict component failures},
interhash = {2cbfae1d8dd1aa5a28e42877aec75f32},
intrahash = {37bb9df82b14e322d859d4f180d1c861},
isbn = {1-59593-375-1},
keywords = {imported},
location = {Shanghai, China},
month = {September},
pages = {452--461},
publisher = {ACM},
timestamp = {2007-11-23T17:50:43.000+0100},
title = {Mining metrics to predict component failures},
url = {http://doi.acm.org/10.1145/1134285.1134349},
year = 2006
}