{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T08:24:22Z","timestamp":1770279862198,"version":"3.49.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2014,1,15]],"date-time":"2014-01-15T00:00:00Z","timestamp":1389744000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2015,4]]},"DOI":"10.1007\/s10664-013-9292-6","type":"journal-article","created":{"date-parts":[[2014,1,14]],"date-time":"2014-01-14T07:09:57Z","timestamp":1389683397000},"page":"294-335","source":"Crossref","is-referenced-by-count":25,"title":["Towards improving statistical modeling of software engineering data: think locally, act globally!"],"prefix":"10.1007","volume":"20","author":[{"given":"Nicolas","family":"Bettenburg","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiyappan","family":"Nagappan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed E.","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,1,15]]},"reference":[{"key":"9292_CR1","unstructured":"Ackerman M, Ben-david S (2009) Clusterability: a theoretical study. In: Proceedings of the twelfth international conference on artificial intelligence and statistics (AISTATS\u201909), JMLR workshop and conference proceedings, vol 5. pp. 1\u20138"},{"issue":"6","key":"9292_CR2","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/TAC.1974.1100705","volume":"19","author":"H Akaike","year":"1974","unstructured":"Akaike H (1974) A new look at the statistical model identification. Autom Control IEEE Trans 19(6):716\u2013723","journal-title":"Autom Control IEEE Trans"},{"key":"9292_CR3","doi-asserted-by":"crossref","unstructured":"Andreou A, Papatheocharous E (2008) Software cost estimation using fuzzy decision trees. In: Automated software engineering, 2008. ASE 2008. 23rd IEEE\/ACM International Conference, pp 371 \u2013374","DOI":"10.1109\/ASE.2008.51"},{"key":"9292_CR4","unstructured":"Attoh-okine N, Mensah S, Nawaiseh M, Hall D (2001) Using multivariate adaptive regression splines (mars) in pavement roughness prediction. Strategy"},{"key":"9292_CR5","doi-asserted-by":"crossref","unstructured":"Barkmann H, Lincke R, Lowe W (2009) Quantitative evaluation of software quality metrics in open-source projects. In: Proceedings of the 2009 international conference on advanced information networking and applications workshops, WAINA \u201909. IEEE Computer Society, Washington, DC, pp 1067\u20131072","DOI":"10.1109\/WAINA.2009.190"},{"key":"9292_CR6","doi-asserted-by":"crossref","unstructured":"Bettenburg N, Hassan AE (2010) Studying the impact of social structures on software quality. In: Proceedings of the 2010 IEEE 18th international conference on program comprehension, ICPC \u201910. IEEE Computer Society, Washington, DC, pp 124\u2013133","DOI":"10.1109\/ICPC.2010.46"},{"key":"9292_CR7","doi-asserted-by":"crossref","unstructured":"Bettenburg N, Nagappan M, Hassan A (2012) Think locally, act globally: improving defect and effort prediction models. In: Mining software repositories (MSR), 2012 9th IEEE working conference. pp 60\u201369","DOI":"10.1109\/MSR.2012.6224300"},{"key":"9292_CR8","doi-asserted-by":"crossref","unstructured":"Di Penta M (2011) Nothing else matters: what predictive model should i use?. In: Proceedings of the 7th international conference on predictive models in software engineering, promise \u201911. ACM, New York, NY,pp 10:1\u201310:3","DOI":"10.1145\/2020390.2020400"},{"key":"9292_CR9","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1016\/j.jss.2007.07.040","volume":"81","author":"KO Elish","year":"2008","unstructured":"Elish KO, Elish MO (2008) Predicting defect-prone software modules using support vector machines. J Syst Softw 81:649\u2013660","journal-title":"J Syst Softw"},{"key":"9292_CR10","unstructured":"Fox J (2008) Applied regression analysis and generalized linear models, 2nd edn. Sage, Los Angeles, London"},{"issue":"2","key":"9292_CR11","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1007\/s00357-007-0004-5","volume":"181","author":"C Fraley","year":"2007","unstructured":"Fraley C (2007) Bayesian regularization for normal mixture estimation and model-based clustering. J Classif 181(2):155\u2013181","journal-title":"J Classif"},{"key":"9292_CR12","doi-asserted-by":"crossref","unstructured":"Fraley C, Raftery AE (2009) Mclust version 3 for R: Normal mixture modeling and model-based clustering. Technical Report 504, University of Washington, Department of Statistics, Seattle, 2006 (subsequent revisions)","DOI":"10.21236\/ADA456562"},{"issue":"1","key":"9292_CR13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1214\/aos\/1176347963","volume":"19","author":"JH Friedman","year":"1991","unstructured":"Friedman JH (1991) Multivariate adaptive regression splines. Ann Stat 19(1):1\u201367","journal-title":"Ann Stat"},{"key":"9292_CR14","doi-asserted-by":"crossref","unstructured":"Harrell FE (2001) With Applications to Linear Models, Logistic Regression, and Survival Analysis, Series: Springer Series in Statistics, 1st ed. 2002. Corr. 2nd printing 2001, XXIII, New York, 571 pp","DOI":"10.1007\/978-1-4757-3462-1_1"},{"issue":"1","key":"9292_CR15","first-page":"100","volume":"28","author":"JA Hartigan","year":"1979","unstructured":"Hartigan JA, Wong MA (1979) A k-means clustering algorithm. JSTOR: Appl Stat 28(1):100\u2013108","journal-title":"JSTOR: Appl Stat"},{"key":"9292_CR16","doi-asserted-by":"crossref","unstructured":"Kamei Y, Matsumoto S, Monden A, Matsumoto Ki, Adams B, Hassan AE (2010) Revisiting common bug prediction findings using effort-aware models. In: Proceedings of the 2010 IEEE international conference on software maintenance, ICSM \u201910. IEEE Computer Society, pp 1\u201310","DOI":"10.1109\/ICSM.2010.5609530"},{"issue":"2","key":"9292_CR17","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/s10515-011-0092-1","volume":"19","author":"M Li","year":"2012","unstructured":"Li M, Zhang H, Wu R, Zhou ZH (2012) Sample-based software defect prediction with active and semi-supervised learning. Autom Softw Eng 19(2):201\u2013230. doi: 10.1007\/s10515-011-0092-1","journal-title":"Autom Softw Eng"},{"issue":"4","key":"9292_CR18","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1177\/001316446602600402","volume":"26","author":"L McQuitty","year":"1966","unstructured":"McQuitty L (1966) Similarity analysis by reciprocal pairs for discrete and continuous data. Educ Psychol Meas 26(4):825\u2013831","journal-title":"Educ Psychol Meas"},{"key":"9292_CR19","doi-asserted-by":"crossref","unstructured":"Menzies T, Butcher A, Cok D, Layman L, Marcus A, Shull F, Turhan B, Zimmermann T (2013) Local vs. global lessons from defect prediction and effort estimation. IEEE Trans Softw Eng (to appear)","DOI":"10.1109\/TSE.2012.83"},{"key":"9292_CR20","doi-asserted-by":"crossref","unstructured":"Menzies T, Butcher A, Marcus A, Zimmermann T, Cok D (2011) Local vs global models for effort estimation and defect prediction. In: Proceedings of the 26th IEEE\/ACM international conference on automated software engineering","DOI":"10.1109\/ASE.2011.6100072"},{"key":"9292_CR21","unstructured":"Menzies T, Caglayan B, Kocaguneli E, Krall J, Peters F, Turhan B (2012) The promise repository of empirical software engineering data. http:\/\/promisedata.googlecode.com"},{"issue":"1","key":"9292_CR22","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1109\/TSE.2007.256941","volume":"33","author":"T Menzies","year":"2007","unstructured":"Menzies T, Greenwald J, Frank A (2007) Data mining static code attributes to learn defect predictors. IEEE Trans Softw Eng 33(1):2\u201313","journal-title":"IEEE Trans Softw Eng"},{"key":"9292_CR23","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1002\/bltj.2229","volume":"5","author":"A Mockus","year":"2000","unstructured":"Mockus A, Weiss DM (2000) Predicting risk of software changes. Bell Labs Tech J 5:169\u2013180","journal-title":"Bell Labs Tech J"},{"key":"9292_CR24","doi-asserted-by":"crossref","unstructured":"Mockus A, Weiss DM, Zhang P (2003) Understanding and predicting effort in software projects. In: Proceedings of the 25th international conference on software engineering, ICSE \u201903. IEEE Computer Society, Washington, DC, pp 274\u2013284","DOI":"10.1109\/ICSE.2003.1201207"},{"key":"9292_CR25","doi-asserted-by":"crossref","unstructured":"Mockus A, Zhang P, Li PL (2005) Predictors of customer perceived software quality. In: Proceedings of the 27th international conference on Software engineering, ICSE \u201905. ACM, New York, NY, pp 225\u2013233","DOI":"10.1145\/1062455.1062506"},{"key":"9292_CR26","doi-asserted-by":"crossref","unstructured":"Nagappan N, Ball T (2005) Use of relative code churn measures to predict system defect density. In: Proceedings of the 27th international conference on software engineering, ICSE \u201905. ACM, pp 284\u2013292","DOI":"10.1145\/1062455.1062514"},{"key":"9292_CR27","doi-asserted-by":"crossref","unstructured":"Nagappan N, Ball T, Zeller A (2006) Mining metrics to predict component failures. In: Proceedings of the 28th international conference on software engineering, ICSE \u201906. ACM, New York, NY, pp 452\u2013461","DOI":"10.1145\/1134285.1134349"},{"key":"9292_CR28","doi-asserted-by":"crossref","unstructured":"Nguyen THD, Adams B, Hassan AE (2010) Studying the impact of dependency network measures on software quality. In: Proceedings of the 2010 IEEE international conference on software maintenance. IEEE Computer Society, pp 1\u201310","DOI":"10.1109\/ICSM.2010.5609560"},{"issue":"1","key":"9292_CR29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.im.2003.09.002","volume":"42","author":"KM Osei-Bryson","year":"2004","unstructured":"Osei-Bryson KM, Ko M (2004) Exploring the relationship between information technology investments and firm performance using regression splines analysis. Inf Manag 42(1):1\u201313","journal-title":"Inf Manag"},{"key":"9292_CR30","doi-asserted-by":"crossref","unstructured":"Posnett D, Filkov V, Devanbu P (2011) Ecological inference in empirical software engineering. Int Conf Autom Softw Eng 362\u2013371","DOI":"10.1109\/ASE.2011.6100074"},{"key":"9292_CR31","first-page":"111","volume":"25","author":"AE Raftery","year":"2007","unstructured":"Raftery AE, Raftery AE (2007) Bayesian model selection in social research adrian e. raftery sociological methodology. Soc Res 25:111\u2013163","journal-title":"Soc Res"},{"key":"9292_CR32","doi-asserted-by":"crossref","unstructured":"Rahman F, Devanbu P (2013) How, and why, process metrics are better. In: Proceedings of the 2013 international conference on software engineering, ICSE \u201913. IEEE Computer Society, Washington, DC, pp 432\u2013441","DOI":"10.1109\/ICSE.2013.6606589"},{"key":"9292_CR33","first-page":"602","volume-title":"Mathematical statistics and data analysis, Series: Wadsworth statistics\/probability series, 2nd ed. illustrated, 1995","author":"JA Rice","year":"2001","unstructured":"Rice JA (2001) Mathematical statistics and data analysis, Series: Wadsworth statistics\/probability series, 2nd ed. illustrated, 1995. Duxbury Press, Pacific Grove, 602 pp"},{"issue":"2","key":"9292_CR34","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","volume":"6","author":"G Schwarz","year":"1978","unstructured":"Schwarz G (1978) Estimating the dimension of a model. Ann Stat 6(2):461\u2013464","journal-title":"Ann Stat"},{"issue":"2","key":"9292_CR35","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1049\/sej.1988.0003","volume":"3","author":"M Shepperd","year":"1988","unstructured":"Shepperd M (1988) A critique of cyclomatic complexity as a software metric. Softw Eng J 3(2):30\u201336","journal-title":"Softw Eng J"},{"key":"9292_CR36","doi-asserted-by":"crossref","unstructured":"Shihab E, Bird C, Zimmermann T, Zimmermann T (2012) The effect of branching strategies on software quality. In: ESEM. pp 301\u2013310","DOI":"10.1145\/2372251.2372305"},{"key":"9292_CR37","volume-title":"Data Mining: practical machine learning tools and techniques, 2nd edn (Morgan Kaufmann Series in Data Management Systems)","author":"IH Witten","year":"2005","unstructured":"Witten IH, Frank E (2005) Data Mining: practical machine learning tools and techniques, 2nd edn (Morgan Kaufmann Series in Data Management Systems). Morgan Kaufmann Publishers Inc., San Francisco"},{"key":"9292_CR38","doi-asserted-by":"crossref","first-page":"S649","DOI":"10.1002\/gepi.2001.21.s1.s649","volume":"21 Suppl 1","author":"TP York","year":"2001","unstructured":"York TP, Eaves LJ (2001) Common disease analysis using multivariate adaptive regression splines (mars): Genetic analysis workshop 12 simulated sequence data. Genet Epidemiol 21 Suppl 1:S649\u2013S654","journal-title":"Genet Epidemiol"},{"key":"9292_CR39","doi-asserted-by":"crossref","unstructured":"Zimmermann T, Nagappan N, Gall H, Giger E, Murphy B (2009) Cross-project defect prediction: a large scale experiment on data vs. domain vs. process. In: Proceedings of the the 7th joint meeting of the European software engineering conference and the ACM SIGSOFT symposium on the foundations of software engineering, ESEC\/FSE \u201909. ACM, New York, NY, pp 91\u2013100","DOI":"10.1145\/1595696.1595713"},{"key":"9292_CR40","doi-asserted-by":"crossref","unstructured":"Zimmermann T, Premraj R, Zeller A (2007) Predicting defects for eclipse. In: Proceedings of the third international workshop on predictor models in software engineering, PROMISE \u201907. IEEE Computer Society, Washington, DC, p 9","DOI":"10.1109\/PROMISE.2007.10"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-013-9292-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10664-013-9292-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-013-9292-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,23]],"date-time":"2022-03-23T11:57:10Z","timestamp":1648036630000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10664-013-9292-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,1,15]]},"references-count":40,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2015,4]]}},"alternative-id":["9292"],"URL":"https:\/\/doi.org\/10.1007\/s10664-013-9292-6","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,1,15]]}}}