\begin{thebibliography}{10}
\providecommand{\url}[1]{#1}
\csname url@rmstyle\endcsname
\providecommand{\newblock}{\relax}
\providecommand{\bibinfo}[2]{#2}
\providecommand\BIBentrySTDinterwordspacing{\spaceskip=0pt\relax}
\providecommand\BIBentryALTinterwordstretchfactor{4}
\providecommand\BIBentryALTinterwordspacing{\spaceskip=\fontdimen2\font plus
\BIBentryALTinterwordstretchfactor\fontdimen3\font minus
  \fontdimen4\font\relax}
\providecommand\BIBforeignlanguage[2]{{%
\expandafter\ifx\csname l@#1\endcsname\relax
\typeout{** WARNING: IEEEtran.bst: No hyphenation pattern has been}%
\typeout{** loaded for the language `#1'. Using the pattern for}%
\typeout{** the default language instead.}%
\else
\language=\csname l@#1\endcsname
\fi
#2}}

\bibitem{me06d}
T.~Menzies, Z.~Chen, J.~Hihn, and K.~Lum, ``Selecting best practices for effort
  estimation,'' \emph{IEEE Transactions on Software Engineering}, November
  2006, available from \url{http://menzies.us/pdf/06coseekmo.pdf}.

\bibitem{kitch07}
B.~A. Kitchenham, E.~Mendes, and G.~H. Travassos, ``Cross- vs. within-company
  cost estimation studies: A systematic review,'' \emph{IEEE Transactions on
  Software Engineering}, pp. 316--329, May 2007.

\bibitem{mendes07}
E.~Mendes, G.~Dinakaran, and N.~Mosley, ``How valuable is it for a web company
  to use a cross-company cost model, compared to using its own single-company
  model?'' in \emph{16th International World Wide Web Conference, Banff,
  Canada, May 8-12}, 2007, available from
  \url{http://www2007.org/paper326.php}.

\bibitem{abrahamsson07}
P.~Abrahamsson, R.~Moser, W.~Pedrycz, A.~Sillitti, and G.~Succi, ``Effort
  prediction in iterative software development processes -- incremental versus
  global prediction models,'' in \emph{First International Symposium on
  Empirical Software Engineering and Measurement (ESEM 2007)}, 2007, pp.
  344--353.

\bibitem{macdonell07}
S.~MacDonell and M.~Shepperd, ``Comparing local and global software effort
  estimation models -- reflections on a systematic review,'' in \emph{Empirical
  Software Engineering and Measurement, ESEM 2007}, 2007, pp. 401--409.

\bibitem{Premraj:2007p1626}
\BIBentryALTinterwordspacing
R.~Premraj and T.~Zimmermann, ``Building software cost estimation models using
  homogenous data,'' \emph{Empirical Software Engineering and Measurement}, Jan
  2007. [Online]. Available:
  \url{http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4343767}
\BIBentrySTDinterwordspacing

\bibitem{boehm00a}
B.~Boehm, ``Safe and simple software cost analysis,'' \emph{IEEE Software}, pp.
  14--17, September/October 2000, available from
  \url{http://www.computer.org/certification/beta/Boehm_Safe.pdf}.

\bibitem{me07b}
T.~Menzies, J.~Greenwald, and A.~Frank, ``Data mining static code attributes to
  learn defect predictors,'' \emph{IEEE Transactions on Software Engineering},
  January 2007, available from \url{http://menzies.us/pdf/06learnPredict.pdf}.

\bibitem{mccabe76}
T.~McCabe, ``A complexity measure,'' \emph{IEEE Transactions on Software
  Engineering}, vol.~2, no.~4, pp. 308--320, Dec. 1976.

\bibitem{halstead77}
M.~Halstead, \emph{Elements of Software Science}.\hskip 1em plus 0.5em minus
  0.4em\relax Elsevier, 1977.

\bibitem{shu02}
F.~Shull, V.~Basili, B.~Boehm, A.~Brown, P.~Costa, M.~Lindvall, D.~Port,
  I.~Rus, R.~Tesoriero, and M.~Zelkowitz, ``What we have learned about fighting
  defects,'' in \emph{Proceedings of 8th International Software Metrics
  Symposium, Ottawa, Canada}, 2002, pp. 249--258, available from
  \url{http://fc-md.umd.edu/fcmd/Papers/shull_defects.ps}.

\bibitem{fagan86}
M.~Fagan, ``Advances in software inspections,'' \emph{IEEE Trans. on Software
  Engineering}, pp. 744--751, July 1986.

\bibitem{shull00a}
F.~Shull, I.~Rus, and V.~Basili, ``How perspective-based reading can improve
  requirements inspections,'' \emph{IEEE Computer}, vol.~33, no.~7, pp. 73--79,
  2000, available from
  \url{http://www.cs.umd.edu/projects/SoftEng/ESEG/papers/82.77.pdf}.

\bibitem{fagan76}
M.~Fagan, ``Design and code inspections to reduce errors in program
  development,'' \emph{IBM Systems Journal}, vol.~15, no.~3, 1976.

\bibitem{conf/icse/NagappanB05a}
\BIBentryALTinterwordspacing
N.~Nagappan and T.~Ball, ``Static analysis tools as early indicators of
  pre-release defect density,'' in \emph{ICSE}, 2005, pp. 580--586. [Online].
  Available: \url{http://doi.acm.org/10.1145/1062558}
\BIBentrySTDinterwordspacing

\bibitem{me02f}
T.~Menzies, D.~Raffo, S.~on~Setamanit, Y.~Hu, and S.~Tootoonian, ``Model-based
  tests of truisms,'' in \emph{Proceedings of IEEE ASE 2002}, 2002, available
  from \url{http://menzies.us/pdf/02truisms.pdf}.

\bibitem{chapman02}
M.~Chapman and D.~Solomon, ``The relationship of cyclomatic complexity,
  essential complexity and error rates,'' 2002, proceedings of the NASA
  Software Assurance Symposium, Coolfont Resort and Conference Center in
  Berkley Springs, West Virginia. Available from
  \url{http://www.ivv.nasa.gov/business/research/osmasas/conclusion2002/Mike_C%
hapman_The_Relationship_of_Cyclomatic_Complexity_Essential_Complexity_and_Erro%
r_Rates.ppt}.

\bibitem{me04g}
T.~Menzies, J.~DiStefano, A.~Orrego, and R.~Chapman, ``Assessing predictors of
  software defects,'' in \emph{Proceedings, workshop on Predictive Software
  Models, Chicago}, 2004, available from \url{http://menzies.us/pdf/04psm.pdf}.

\bibitem{polyspace}
``Polyspace verifier$^{\mbox \textregistered}$,'' 2005, available from
  \url{http://www.di.ens.fr/~cousot/projects/DAEDALUS/synthetic_summary/POLYSP%
ACE/polyspace-daedalus.htm}.

\bibitem{hall00}
G.~Hall and J.~Munson, ``Software evolution: code delta and code churn,''
  \emph{Journal of Systems and Software}, pp. 111 -- 118, 2000.

\bibitem{nikora03}
A.~Nikora and J.~Munson, ``Developing fault predictors for evolving software
  systems,'' in \emph{Ninth International Software Metrics Symposium
  (METRICS'03)}, 2003.

\bibitem{khoshgoftaar01}
T.~Khoshgoftaar, ``An application of zero-inflated poisson regression for
  software fault prediction,'' in \emph{Proceedings of the 12th International
  Symposium on Software Reliability Engineering, Hong Kong}, Nov 2001, pp.
  66--73.

\bibitem{Khoshgoftaar:2004p1877}
T.~Khoshgoftaar and N.~Seliya, ``Comparative assessment of software quality
  classification techniques: An empirical case study,'' \emph{Empirical
  Software Engineering}, vol.~9, no.~3, pp. 229--257, 2004.

\bibitem{conf/ictai/TangK04}
\BIBentryALTinterwordspacing
W.~Tang and T.~M. Khoshgoftaar, ``Noise identification with the k-means
  algorithm,'' in \emph{ICTAI}, 2004, pp. 373--378. [Online]. Available:
  \url{http://doi.ieeecomputersociety.org/10.1109/ICTAI.2004.93}
\BIBentrySTDinterwordspacing

\bibitem{journals/ese/KhoshgoftaarS03}
\BIBentryALTinterwordspacing
T.~M. Khoshgoftaar and N.~Seliya, ``Fault prediction modeling for software
  quality estimation: Comparing commonly used techniques,'' \emph{Empirical
  Software Engineering}, vol.~8, no.~3, pp. 255--283, 2003. [Online].
  Available: \url{http://dx.doi.org/10.1023/A:1024424811345}
\BIBentrySTDinterwordspacing

\bibitem{me03a}
T.~Menzies, J.~D. Stefano, K.~Ammar, K.~McGill, P.~Callis, R.~Chapman, and
  D.~J, ``When can we test less?'' in \emph{IEEE Metrics'03}, 2003, available
  from \url{http://menzies.us/pdf/03metrics.pdf}.

\bibitem{me02e}
T.~Menzies, J.~S. DiStefeno, M.~Chapman, and K.~Mcgill, ``Metrics that
  matter,'' in \emph{27th NASA SEL workshop on Software Engineering}, 2002,
  available from \url{http://menzies.us/pdf/02metrics.pdf}.

\bibitem{me03k}
T.~Menzies, J.~D. Stefano, and M.~Chapman, ``Learning early lifecycle {IVV}
  quality indicators,'' in \emph{IEEE Metrics '03}, 2003, available from
  \url{http://menzies.us/pdf/03early.pdf}.

\bibitem{me03q}
T.~Menzies and J.~S.~D. Stefano, ``How good is your blind spot sampling
  policy?'' in \emph{2004 IEEE Conference on High Assurance Software
  Engineering}, 2003, available from \url{http://menzies.us/pdf/03blind.pdf}.

\bibitem{porter90}
A.~Porter and R.~Selby, ``Empirically guided software development using
  metric-based classification trees,'' \emph{IEEE Software}, pp. 46--54, March
  1990.

\bibitem{tiang95}
J.~Tian and M.~Zelkowitz, ``Complexity measure evaluation and selection,''
  \emph{IEEE Transaction on Software Engineering}, vol.~21, no.~8, pp.
  641--649, Aug. 1995.

\bibitem{khoshgoftaar99}
T.~Khoshgoftaar and E.~Allen, ``Model software quality with classification
  trees,'' in \emph{Recent Advances in Reliability and Quality Engineering},
  H.~Pham, Ed.\hskip 1em plus 0.5em minus 0.4em\relax World Scientific, 2001,
  pp. 247--270.

\bibitem{srinivasan95}
K.~Srinivasan and D.~Fisher, ``Machine learning approaches to estimating
  software development effort,'' \emph{IEEE Trans. Soft. Eng.}, pp. 126--137,
  February 1995.

\bibitem{rakitin01}
S.~Rakitin, \emph{Software Verification and Validation for Practitioners and
  Managers, Second Edition}.\hskip 1em plus 0.5em minus 0.4em\relax Artech
  House, 2001.

\bibitem{graves00}
T.~L. Graves, A.~F. Karr, J.~S. Marron, and H.~P. Siy, ``Predicting fault
  incidence using software change history,'' \emph{IEEE Trans. Software Eng.},
  vol.~26, no.~7, pp. 653--661, 2000, available on-line at
  \url{www.niss.org/technicalreports/tr80.pdf}.

\bibitem{Blake+Merz:1998}
C.~Blake and C.~Merz, ``{UCI} repository of machine learning databases,'' 1998,
  uRL: \url{http://www.ics.uci.edu/~mlearn/MLRepository.html}.

\bibitem{fenton96}
N.~E. Fenton and S.~Pfleeger, \emph{Software Metrics: A Rigorous \& Practical
  Approach (second edition)}.\hskip 1em plus 0.5em minus 0.4em\relax
  International Thompson Press, 1995.

\bibitem{shepperd94}
M.~Shepperd and D.~Ince, ``A critique of three metrics,'' \emph{The Journal of
  Systems and Software}, vol.~26, no.~3, pp. 197--210, September 1994.

\bibitem{brooks95}
F.~P. Brooks, \emph{The Mythical Man-Month, Anniversary edition}.\hskip 1em
  plus 0.5em minus 0.4em\relax Addison-Wesley, 1995.

\bibitem{nach08}
V.~B. Nachiappan~Nagappan, Brendan~Murphy, ``The influence of organizational
  structure on software quality: An empirical case study,'' in \emph{ICSE'08},
  2008.

\bibitem{jiang07}
Y.~Jiang, B.~Cukic, and T.~Menzies, ``Fault prediction using early lifecycle
  data,'' in \emph{ISSRE'07}, 2007, available from
  \url{http://menzies.us/pdf/07issre.pdf}.

\bibitem{me07c}
G.~Boetticher, T.~Menzies, and T.~Ostrand, ``The {PROMISE} {R}epository of
  {E}mpirical {S}oftware {E}ngineering {D}ata,'' 2007,
  \url{http://promisedata.org/repository}.

\bibitem{kim08}
S.~Kim, J.~Whitehead, and Y.~Zhang, ``Classifying software changes: Clean or
  buggy?'' \emph{IEEE TSE}, pp. 181--196, March/April 2008.

\bibitem{basili02}
V.~Basili, F.~McGarry, R.~Pajerski, and M.~Zelkowitz, ``Lessons learned from 25
  years of process improvement: The rise and fall of the {NASA} software
  engineering laboratory,'' in \emph{Proceedings of the 24th International
  Conference on Software Engineering (ICSE) 2002, Orlando, Florida}, 2002,
  available from
  \url{http://www.cs.umd.edu/projects/SoftEng/ESEG/papers/83.88.pdf}.

\bibitem{drummond03}
C.~Drummond and R.~C. Holte, ``C4.5, class imbalance, and cost sensitivity: why
  under-sampling beats over-sampling,'' in \emph{Workshop on Learning from
  Imbalanced Datasets II}, 2003.

\bibitem{cohen95r}
W.~Cohen, ``Fast effective rule induction,'' in \emph{ICML'95}, 1995, pp.
  115--123, available on-line from
  \url{http://www.cs.cmu.edu/~wcohen/postscript/ml-95-ripper.ps}.

\bibitem{quinlan92}
R.~Quinlan, \emph{C4.5: Programs for Machine Learning}.\hskip 1em plus 0.5em
  minus 0.4em\relax Morgan Kaufman, 1992, iSBN: 1558602380.

\bibitem{holte93}
R.~Holte, ``Very simple classification rules perform well on most commonly used
  datasets,'' \emph{Machine Learning}, vol.~11, p.~63, 1993.

\bibitem{brieman96}
L.~Brieman, ``Bagging predictors,'' \emph{Machine Learning}, vol.~24, no.~2,
  pp. 123--140, 1996.

\bibitem{FreSch97}
Y.~Freund and R.~Schapire, ``A decision-theoretic generalization of on-line
  learning and an application to boosting,'' \emph{JCSS: Journal of Computer
  and System Sciences}, vol.~55, 1997.

\bibitem{lessmann09}
S.~Lessmann, B.~Baesens, C.~Mues, and S.~Pietsch, ``Benchmarking classification
  models for software defect prediction: A proposed framework and novel
  findings,'' \emph{accepted for publication IEEE Transactions on Software
  Engineering}, 2009.

\bibitem{witten05}
I.~H. Witten and E.~Frank, \emph{Data mining. 2nd edition}.\hskip 1em plus
  0.5em minus 0.4em\relax Los Altos, US: Morgan Kaufmann, 2005.

\bibitem{turhan07qsic}
B.~Turhan and A.~Bener, ``A multivariate analysis of static code attributes for
  defect prediction,'' in \emph{Proceedings of the Seventh International
  Conference on Quality Software}.\hskip 1em plus 0.5em minus 0.4em\relax Los
  Alamitos, CA, USA: IEEE Computer Society, 2007, pp. 231--237.

\bibitem{domingos97optimality}
\BIBentryALTinterwordspacing
P.~Domingos and M.~J. Pazzani, ``On the optimality of the simple bayesian
  classifier under zero-one loss,'' \emph{Machine Learning}, vol.~29, no. 2-3,
  pp. 103--130, 1997. [Online]. Available:
  \url{citeseer.ist.psu.edu/domingos97optimality.html}
\BIBentrySTDinterwordspacing

\bibitem{me07e}
T.~Menzies, A.~Dekhtyar, J.~Distefano, and J.~Greenwald, ``Problems with
  precision,'' \emph{IEEE Transactions on Software Engineering}, September
  2007, \url{http://menzies.us/pdf/07precision.pdf}.

\bibitem{mann47}
H.~B. Mann and D.~R. Whitney, ``On a test of whether one of two random
  variables is stochastically larger than the other,'' \emph{Ann. Math.
  Statist.}, vol.~18, no.~1, pp. 50--60, 1947, available on-line at
  \url{http://projecteuclid.org/DPubS?service=UI&version=1.0&verb=Display&hand%
le=euclid.aoms/1177730491}.

\bibitem{demsar06}
J.~Demsar, ``Statistical comparisons of clasifiers over multiple data sets,''
  \emph{Journal of Machine Learning Research}, vol.~7, pp. 1--30, 2006,
  avaliable from \url{http://jmlr.csail.mit.edu/papers/v7/demsar06a.html}.

\bibitem{hayes06}
\BIBentryALTinterwordspacing
J.~H. Hayes, A.~Dekhtyar, and S.~K. Sundaram, ``Advancing candidate link
  generation for requirements tracing: The study of methods,'' \emph{IEEE
  Trans. Software Eng}, vol.~32, no.~1, pp. 4--19, 2006. [Online]. Available:
  \url{http://doi.ieeecomputersociety.org/10.1109/TSE.2006.3}
\BIBentrySTDinterwordspacing

\bibitem{fenton97}
N.~E. Fenton and S.~Pfleeger, \emph{Software Metrics: A Rigorous \& Practical
  Approach}.\hskip 1em plus 0.5em minus 0.4em\relax International Thompson
  Press, 1997.

\bibitem{me08d}
T.~Menzies, B.~Turhan, A.~Bener, G.~Gay, B.~Cukic, and Y.~Jiang, ``Implications
  of ceiling effects in defect predictors,'' in \emph{Proceedings of PROMISE
  2008 Workshop (ICSE)}, 2008, available from
  \url{http://menzies.us/pdf/08ceiling.pdf}.

\bibitem{orrego04}
A.~Orrego, ``Sawtooth: Learning from huge amounts of data,'' Master's thesis,
  Computer Science, West Virginia University, 2004.

\bibitem{quinlan92b}
J.~R. Quinlan, ``Learning with {C}ontinuous {C}lasses,'' in \emph{5th
  Australian Joint Conference on Artificial Intelligence}, 1992, pp. 343--348,
  available from \url{http://citeseer.nj.nec.com/quinlan92learning.html}.

\bibitem{john95}
G.~John and P.~Langley, ``Estimating continuous distributions in bayesian
  classifiers,'' in \emph{Proceedings of the Eleventh Conference on Uncertainty
  in Artificial Intelligence Montreal, Quebec: Morgan Kaufmann}, 1995, pp.
  338--345, available from
  \url{http://citeseer.ist.psu.edu/john95estimating.html}.

\end{thebibliography}