{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T07:27:59Z","timestamp":1769844479795,"version":"3.49.0"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T00:00:00Z","timestamp":1626912000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T00:00:00Z","timestamp":1626912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1007\/s10664-021-09991-3","type":"journal-article","created":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T14:03:16Z","timestamp":1626962596000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Does class size matter? An in-depth assessment of the effect of class size in software defect prediction"],"prefix":"10.1007","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9454-1366","authenticated-orcid":false,"given":"Amjed","family":"Tahir","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwabena E.","family":"Bennin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen G.","family":"MacDonell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,22]]},"reference":[{"issue":"6","key":"9991_CR1","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1037\/0022-3514.51.6.1173","volume":"51","author":"RM Baron","year":"1986","unstructured":"Baron RM, Kenny DA (1986) The moderator\u2013mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. J Pers Soc Psychol 51(6):1173","journal-title":"J Pers Soc Psychol"},{"issue":"10","key":"9991_CR2","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1109\/32.544352","volume":"22","author":"VR Basili","year":"1996","unstructured":"Basili VR, Briand LC, Melo WL (1996a) A validation of object-oriented design metrics as quality indicators. IEEE Trans Softw Eng 22(10):751\u2013761","journal-title":"IEEE Trans Softw Eng"},{"issue":"10","key":"9991_CR3","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1145\/236156.236184","volume":"39","author":"VR Basili","year":"1996","unstructured":"Basili VR, Briand LC, Melo WLWL (1996b) How reuse influences productivity in object-oriented systems. Commun ACM 39(10):104\u2013116","journal-title":"Commun ACM"},{"key":"9991_CR4","doi-asserted-by":"crossref","unstructured":"Bennin KE, Keung J, Phannachitta P, Monden A, Mensah S (2018) Mahakil: Diversity based oversampling approach to alleviate the class imbalance issue in software defect prediction. IEEE Trans Softw Eng 44(6)","DOI":"10.1109\/TSE.2017.2731766"},{"issue":"2","key":"9991_CR5","first-page":"1","volume":"24","author":"KE Bennin","year":"2018","unstructured":"Bennin KE, Keung J, Monden A (2018) On the relative value of data resampling approaches for software defect prediction. Empir Softw Eng 24(2):1\u201335","journal-title":"Empir Softw Eng"},{"key":"9991_CR6","unstructured":"Binkley AB, Schach SR (1998) Validation of the coupling dependency metric as a predictor of run-time failures and maintenance measures. In: Proceedings of the 20th International conference on software engineering. IEEE"},{"key":"9991_CR7","doi-asserted-by":"publisher","first-page":"115","DOI":"10.2307\/271084","volume":"20","author":"K Bollen","year":"1990","unstructured":"Bollen K, Stinet R (1990) Direct and indirect effects : classical and bootstrap estimates of variability. Sociol Methodol 20:115\u2013140","journal-title":"Sociol Methodol"},{"issue":"3","key":"9991_CR8","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/S0164-1212(99)00102-8","volume":"51","author":"LC Briand","year":"2000","unstructured":"Briand LC, W\u00fcst J., Daly JW, Porter DV (2000) Exploring the relationships between design measures and software quality in object-oriented systems. J Syst Softw 51(3):245\u2013273","journal-title":"J Syst Softw"},{"issue":"8","key":"9991_CR9","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.1016\/j.ins.2008.12.001","volume":"179","author":"C Catal","year":"2009","unstructured":"Catal C, Diri B (2009) Investigating the effect of dataset size, metrics sets, and feature selection techniques on software fault prediction problem. Inform Sci 179(8):1040\u20131058","journal-title":"Inform Sci"},{"issue":"6","key":"9991_CR10","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1109\/32.295895","volume":"20","author":"S Chidamber","year":"1994","unstructured":"Chidamber S, Kemerer C (1994) A metrics suite for object oriented design. IEEE Trans Softw Eng 20(6):476\u2013493","journal-title":"IEEE Trans Softw Eng"},{"issue":"4-5","key":"9991_CR11","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s10664-011-9173-9","volume":"17","author":"M D\u2019Ambros","year":"2012","unstructured":"D\u2019Ambros M, Lanza M, Robbes R (2012a) Evaluating defect prediction approaches: a benchmark and an extensive comparison. Empir Softw Eng 17(4-5):531\u2013577","journal-title":"Empir Softw Eng"},{"issue":"4-5","key":"9991_CR12","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s10664-011-9173-9","volume":"17","author":"M D\u2019Ambros","year":"2012","unstructured":"D\u2019Ambros M, Lanza M, Robbes R (2012b) Evaluating defect prediction approaches: a benchmark and an extensive comparison. Empir Softw Eng 17(4-5):531\u2013577","journal-title":"Empir Softw Eng"},{"key":"9991_CR13","doi-asserted-by":"crossref","unstructured":"Dickinson W, Leon D, Fodgurski A (2001) Finding failures by cluster analysis of execution profiles. In: Proceedings of the 23rd International conference on software engineering. IEEE, pp 339\u2013348","DOI":"10.1109\/ICSE.2001.919107"},{"issue":"7","key":"9991_CR14","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1109\/32.935855","volume":"27","author":"K El Emam","year":"2001","unstructured":"El Emam K, Benlarbi S, Goel N, Rai SN (2001) The confounding effect of class size on the validity of object-oriented metrics. IEEE Trans Softw Eng 27(7):630\u2013650","journal-title":"IEEE Trans Softw Eng"},{"issue":"7","key":"9991_CR15","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1109\/TSE.2003.1214331","volume":"29","author":"WM Evanco","year":"2003","unstructured":"Evanco WM (2003) Comments on \u201cthe confounding effect of class size on the validity of object-oriented metrics\u201d. IEEE Trans Softw Eng 29(7):670\u2013672","journal-title":"IEEE Trans Softw Eng"},{"issue":"5","key":"9991_CR16","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1109\/32.815326","volume":"25","author":"NE Fenton","year":"1999","unstructured":"Fenton NE, Neil M (1999) A critique of software defect prediction models. IEEE Trans Softw Eng 25(5):675\u2013689","journal-title":"IEEE Trans Softw Eng"},{"issue":"3","key":"9991_CR17","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1111\/j.1467-9280.2007.01882.x","volume":"18","author":"MS Fritz","year":"2007","unstructured":"Fritz MS, Mackinnon DP (2007) Required sample size to detect the mediated effect. Psychol Sci 18(3):233\u2013239","journal-title":"Psychol Sci"},{"key":"9991_CR18","doi-asserted-by":"crossref","unstructured":"Ghotra B, McIntosh S, Hassan AE (2015) Revisiting the impact of classification techniques on the performance of defect prediction models. In: Proceedings of the 37th International conference on software engineering. IEEE, pp 789\u2013800","DOI":"10.1109\/ICSE.2015.91"},{"issue":"5","key":"9991_CR19","doi-asserted-by":"publisher","first-page":"2585","DOI":"10.1007\/s10664-017-9513-5","volume":"22","author":"Y Gil","year":"2017","unstructured":"Gil Y, Lalouche G (2017) On the correlation between size and metric validity. Empir Softw Eng 22(5):2585\u20132611","journal-title":"Empir Softw Eng"},{"issue":"10","key":"9991_CR20","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1109\/TSE.2005.112","volume":"31","author":"T Gyimothy","year":"2005","unstructured":"Gyimothy T, Ferenc R, Siket I (2005) Empirical validation of object-oriented metrics on open source software for fault prediction. IEEE Trans Softw Eng 31(10):897\u2013910","journal-title":"IEEE Trans Softw Eng"},{"issue":"6","key":"9991_CR21","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1109\/TSE.2011.103","volume":"38","author":"T Hall","year":"2011","unstructured":"Hall T, Beecham S, Bowes D, Gray D, Counsell S (2011) A systematic review of fault prediction performance in software engineering. IEEE Trans Softw Eng 38(6):1276\u20131304","journal-title":"IEEE Trans Softw Eng"},{"key":"9991_CR22","unstructured":"Harrison R, Counsell S, Nithi R (1998) Coupling metrics for object-oriented design. In: Proceedings of 5th International software metrics symposium. IEEE"},{"key":"9991_CR23","unstructured":"Hassan AE (78) Predicting faults using the complexity of code changes. In: Proceedings of the International conference on software engineering"},{"issue":"2","key":"9991_CR24","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1587\/transinf.2020EDL8098","volume":"104","author":"T Hayakawa","year":"2021","unstructured":"Hayakawa T, Tsunoda M, Toda K, Nakasai K, Tahir A, Bennin KE, Monden A, Matsumoto K (2021) A novel approach to address external validity issues in fault prediction using bandit algorithms. IEICE Trans Inf Syst 104(2):327\u2013331","journal-title":"IEICE Trans Inf Syst"},{"issue":"4","key":"9991_CR25","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1080\/03637750903310360","volume":"76","author":"AF Hayes","year":"2009","unstructured":"Hayes AF (2009) Beyond Baron and Kenny: statistical mediation analysis in the new millennium. Commun Monogr 76(4):408\u2013420","journal-title":"Commun Monogr"},{"key":"9991_CR26","volume-title":"Introduction to mediation, moderation and conditional process analysis: a regression-based approach","author":"AF Hayes","year":"2013","unstructured":"Hayes AF (2013) Introduction to mediation, moderation and conditional process analysis: a regression-based approach. Guilford Press, New York"},{"issue":"2","key":"9991_CR27","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s10515-011-0090-3","volume":"19","author":"Z He","year":"2012","unstructured":"He Z, Shu F, Yang Y, Li M, Wang Q (2012) An investigation on the feasibility of cross-project defect prediction. Autom Softw Eng 19 (2):167\u2013199","journal-title":"Autom Softw Eng"},{"key":"9991_CR28","unstructured":"Herraiz I, Hassan AE (2010) Beyond lines of code: Do we need more complexity metrics?. Making software: what really works, and why we believe it, pp 125\u2013141"},{"key":"9991_CR29","doi-asserted-by":"crossref","unstructured":"Johnson PE, Grothendieck G (2012) rockchalk: Regression estimation and presentation. R package version 1(2)","DOI":"10.32614\/CRAN.package.rockchalk"},{"key":"9991_CR30","doi-asserted-by":"crossref","unstructured":"Jureczko M, Madeyski L (2010) Towards identifying software project clusters with regard to defect prediction. In: Proceedings of the 6th international conference on predictive models in software engineering. ACM","DOI":"10.1145\/1868328.1868342"},{"issue":"5","key":"9991_CR31","doi-asserted-by":"publisher","first-page":"2072","DOI":"10.1007\/s10664-015-9400-x","volume":"21","author":"Y Kamei","year":"2016","unstructured":"Kamei Y, Fukushima T, McIntosh S, Yamashita K, Ubayashi N, Hassan AE (2016) Studying just-in-time defect prediction using cross-project models. Empir Softw Eng 21(5):2072\u20132106","journal-title":"Empir Softw Eng"},{"issue":"6","key":"9991_CR32","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1109\/TSE.2012.70","volume":"39","author":"Y Kamei","year":"2013","unstructured":"Kamei Y, Shihab E, Adams B, Hassan AE, Mockus A, Sinha A, Ubayashi N (2013) A large-scale empirical study of just-in-time quality assurance. IEEE Trans Softw Eng 39(6):757\u2013773","journal-title":"IEEE Trans Softw Eng"},{"issue":"1","key":"9991_CR33","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/s10664-014-9354-4","volume":"21","author":"B Kitchenham","year":"2016","unstructured":"Kitchenham B, Madeyski L, Budgen D, Keung J, Brereton P, Charters S, Gibbs S, Pohthong A (2016) Robust statistical methods for empirical software engineering. Empir Softw Eng 21(1):212\u2013259","journal-title":"Empir Softw Eng"},{"issue":"1","key":"9991_CR34","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1037\/1082-989X.7.1.83","volume":"7","author":"DP MacKinnon","year":"2002","unstructured":"MacKinnon DP, Lockwood CM, Hoffman JM, West SG, Sheets V (2002) A comparison of methods to test mediation and other intervening variable effects. Psychol Methods 7(1):83\u2013104","journal-title":"Psychol Methods"},{"issue":"1","key":"9991_CR35","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1207\/s15327906mbr3901_4","volume":"39","author":"DP MacKinnon","year":"2004","unstructured":"MacKinnon DP, Lockwood CM, Williams J (2004) Comparison of approaches in estimating interaction and quadratic effects of latent variables. Multivar Behav Res 39(1):37\u201367","journal-title":"Multivar Behav Res"},{"key":"9991_CR36","unstructured":"Majumder S, Mody P, Menzies T (2020) Revisiting process versus product metrics: a large scale analysis. arXiv:2008.09569"},{"issue":"7","key":"9991_CR37","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1136\/oem.2002.001115","volume":"62","author":"R McNamee","year":"2005","unstructured":"McNamee R (2005) Regression modelling and other methods to control confounding. Occup Environ Med 62(7):500\u2013506","journal-title":"Occup Environ Med"},{"key":"9991_CR38","doi-asserted-by":"crossref","unstructured":"Mende T., Koschke R (2009) Revisiting the evaluation of defect prediction models. In: Proceedings of the 5th International conference on predictor models in software engineering. ACM","DOI":"10.1145\/1540438.1540448"},{"issue":"6","key":"9991_CR39","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1109\/TSE.2007.1015","volume":"33","author":"HM Olague","year":"2007","unstructured":"Olague HM, Etzkorn LH, Gholston S, Quattlebaum S (2007) Empirical validation of three software metrics suites to predict fault-proneness of object-oriented classes developed using highly iterative or agile software development processes. IEEE Trans Softw Eng 33(6):402\u2013419","journal-title":"IEEE Trans Softw Eng"},{"key":"9991_CR40","unstructured":"Osman H, Ghafari M, Nierstrasz O (2018) The impact of feature selection on predicting the number of bugs. arXiv:1807.04486"},{"key":"9991_CR41","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.jss.2018.12.001","volume":"150","author":"L Pascarella","year":"2019","unstructured":"Pascarella L, Palomba F, Bacchelli A (2019) Fine-grained just-in-time defect prediction. J Syst Softw 150:22\u201336","journal-title":"J Syst Softw"},{"issue":"3","key":"9991_CR42","doi-asserted-by":"publisher","first-page":"879","DOI":"10.3758\/BRM.40.3.879","volume":"40","author":"KJ Preacher","year":"2008","unstructured":"Preacher KJ, Hayes AF (2008) Asymptotic and resampling strategies for assessing and comparing indirect effects in multiple mediator models. Behav Res Methods 40(3):879\u2013891","journal-title":"Behav Res Methods"},{"key":"9991_CR43","doi-asserted-by":"crossref","unstructured":"Schr\u00f6ter A., Zimmermann T, Zeller A (2006) Predicting component failures at design time. In: Proceedings of the International symposium on empirical software engineering. ACM, pp 18\u201327","DOI":"10.1145\/1159733.1159739"},{"issue":"6","key":"9991_CR44","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/TSE.2014.2322358","volume":"40","author":"M Shepperd","year":"2014","unstructured":"Shepperd M, Bowes D, Hall T (2014) Researcher Bias: The Use of Machine Learning in Software Defect Prediction. IEEE Trans Softw Eng 40(6):603\u2013616","journal-title":"IEEE Trans Softw Eng"},{"issue":"1982","key":"9991_CR45","doi-asserted-by":"publisher","first-page":"290","DOI":"10.2307\/270723","volume":"13","author":"ME Sobel","year":"1982","unstructured":"Sobel ME (1982) Asymptotic confidence intervals for indirect effects in structural equation models. Sociol Methodol 13(1982):290\u2013312","journal-title":"Sociol Methodol"},{"issue":"3","key":"9991_CR46","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/TSE.2010.90","volume":"37","author":"Q Song","year":"2011","unstructured":"Song Q, Jia Z, Shepperd M, Ying S, Liu J (2011) A general software defect-proneness prediction framework. IEEE Trans Softw Eng 37(3):356\u2013370","journal-title":"IEEE Trans Softw Eng"},{"key":"9991_CR47","unstructured":"Tahir A (2021) Does class size matter? online repository and replication package. https:\/\/github.com\/amjedtahir\/size-effect-defect-prediction"},{"key":"9991_CR48","doi-asserted-by":"crossref","unstructured":"Tahir A, Bennin KE, MacDonell SG, Marsland S (2018) Revisiting the size effect in software fault prediction models. In: Proceedings of the 12th International symposium on empirical software engineering and measurement. ACM","DOI":"10.1145\/3239235.3239243"},{"key":"9991_CR49","unstructured":"Tang M.-H., Kao M.-H., Chen M.-H. (1999) An empirical study on object-oriented metrics. In: Proceedings 6th International software metrics symposium. IEEE"},{"key":"9991_CR50","doi-asserted-by":"crossref","unstructured":"Tantithamthavorn C, Hassan AE (2018) An experience report on defect modelling in practice: Pitfalls and challenges. In: Proceedings of the 40th International conference on software engineering: software engineering in practice. IEEE","DOI":"10.1145\/3183519.3183547"},{"key":"9991_CR51","doi-asserted-by":"crossref","unstructured":"Tingley D, Yamamoto T, Hirose K, Keele L, Imai K (2014) Mediation: R package for causal mediation analysis. J Stat Softw 59(5)","DOI":"10.18637\/jss.v059.i05"},{"issue":"5","key":"9991_CR52","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1007\/s10664-008-9103-7","volume":"14","author":"B Turhan","year":"2009","unstructured":"Turhan B, Menzies T, Bener AB, Di Stefano J (2009) On the relative value of cross-company and within-company data for defect prediction. Empir Softw Eng 14(5):540\u2013578","journal-title":"Empir Softw Eng"},{"key":"9991_CR53","doi-asserted-by":"crossref","unstructured":"Ying AT, Murphy GC, Ng R, Chu-Carroll MC (2004) Predicting source code changes by mining change history. IEEE Trans Softw Eng 30(9)","DOI":"10.1109\/TSE.2004.52"},{"key":"9991_CR54","doi-asserted-by":"crossref","unstructured":"Zhang H (2009) An investigation of the relationships between lines of code and defects. In: Proceedings of the international conference on software maintenance. IEEE","DOI":"10.1109\/ICSM.2009.5306304"},{"issue":"10","key":"9991_CR55","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1109\/TSE.2006.102","volume":"32","author":"Y Zhou","year":"2006","unstructured":"Zhou Y, Leung H (2006) Empirical analysis of object-oriented design metrics for predicting high and low severity faults. IEEE Trans Softw Eng 32(10):771\u2013789","journal-title":"IEEE Trans Softw Eng"},{"key":"9991_CR56","doi-asserted-by":"crossref","unstructured":"Zhou Y, Xu B, Leung H, Chen LIN (2014) An in-depth study of the potentially confounding effect of class size in fault prediction. ACM Trans Softw Eng Methodol 23(1)","DOI":"10.1145\/2556777"},{"key":"9991_CR57","doi-asserted-by":"crossref","unstructured":"Zimmermann T, Nagappan N, Zeller A (2008) Predicting bugs from history. In: Software evolution. Springer, pp. 69\u201388","DOI":"10.1007\/978-3-540-76440-3_4"},{"key":"9991_CR58","doi-asserted-by":"crossref","unstructured":"Zimmermann T, Premraj R, Zeller A (2007) Predicting defects for eclipse. In: Proceedings of the 3rd International workshop on predictor models in software engineering","DOI":"10.1109\/PROMISE.2007.10"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-021-09991-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-021-09991-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-021-09991-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T21:07:47Z","timestamp":1725484067000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-021-09991-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,22]]},"references-count":58,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["9991"],"URL":"https:\/\/doi.org\/10.1007\/s10664-021-09991-3","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,22]]},"assertion":[{"value":"27 May 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"106"}}