{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T11:00:59Z","timestamp":1785495659006,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"MCIN\/AEI\/10.13039\/501100011033 and ERDF A way of making Europe","award":["Grant PID2022-137846NB-I00"],"award-info":[{"award-number":["Grant PID2022-137846NB-I00"]}]},{"name":"TeleRiab4Fra: TeleRiabilitazione ad alta tecnologia per il trattamento del paziente FRAgile\u201d","award":["grant n. PNC0000007, CUP: B53C22006950001"],"award-info":[{"award-number":["grant n. PNC0000007, CUP: B53C22006950001"]}]},{"name":"Research Council of Finland","award":["grants n. 359861 and 349488 - MuFAno"],"award-info":[{"award-number":["grants n. 359861 and 349488 - MuFAno"]}]},{"name":"Business Finland","award":["grant 6GSoft"],"award-info":[{"award-number":["grant 6GSoft"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3793302.3793378","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:42:54Z","timestamp":1785494574000},"page":"533-538","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Stop Comparing Apples and Oranges: Matching for Better Results in Mining Software Repositories Studies"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0589-2349","authenticated-orcid":false,"given":"Sabato","family":"Nocera","sequence":"first","affiliation":[{"name":"University of Salerno, Fisciano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5538-8557","authenticated-orcid":false,"given":"Nyyti","family":"Saarim\u00e4ki","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Luxembourg, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0511-5133","authenticated-orcid":false,"given":"Valentina","family":"Lenarduzzi","sequence":"additional","affiliation":[{"name":"University of Southern Denmark, Vejle, Denmark and University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3210-3990","authenticated-orcid":false,"given":"Davide","family":"Taibi","sequence":"additional","affiliation":[{"name":"University of Southern Denmark, Vejle, Denmark and University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8535-9386","authenticated-orcid":false,"given":"Sira","family":"Vegas","sequence":"additional","affiliation":[{"name":"Universidad Polit\u00e9cnica de Madrid, Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEAA64295.2024.00082"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Aylin Alin. 2010. Multicollinearity. Wiley interdisciplinary reviews: computational statistics 2 3 (2010) 370\u2013374.","DOI":"10.1002\/wics.84"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Claudia Ayala Burak Turhan Xavier Franch and Natalia Juristo. 2021. Use and misuse of the term \u201cexperiment\u201d in mining software repositories research. IEEE Transactions on Software Engineering 48 11 (2021) 4229\u20134248.","DOI":"10.1109\/TSE.2021.3113558"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2025113.2025136"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Gabriele Bavota Andrea De Lucia Massimiliano Di Penta Rocco Oliveto and Fabio Palomba. 2015. An experimental investigation on the innate relationship between quality and refactoring. Journal of Systems and Software 107 (2015) 1 \u2013 14.","DOI":"10.1016\/j.jss.2015.05.024"},{"key":"e_1_3_3_2_7_2","volume-title":"Sloc, Cloc and Code","author":"Boyter Ben","unstructured":"Ben Boyter. [n. d.]. Sloc, Cloc and Code. https:\/\/github.com\/boyter\/scc"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Jessica\u00a0M Franklin Jeremy\u00a0A Rassen Diana Ackermann Dorothee\u00a0B Bartels and Sebastian Schneeweiss. 2014. Metrics for covariate balance in cohort studies of causal effects. Statistics in medicine 33 10 (2014) 1685\u20131699.","DOI":"10.1002\/sim.6058"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Hamid Ghorbani. 2019. Mahalanobis distance and its application for detecting multivariate outliers. Facta Universitatis Series: Mathematics and Informatics (2019) 583\u2013595.","DOI":"10.22190\/FUMI1903583G"},{"key":"e_1_3_3_2_10_2","volume-title":"Epidemiology (fifth edition. ed.)","author":"Gordis Leon.","year":"2014","unstructured":"Leon. Gordis. 2014. Epidemiology (fifth edition. ed.). Elsevier Saunders, Philadelphia."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Lorenz Graf-Vlachy and Stefan Wagner. 2024. Cleaning up confounding: accounting for endogeneity using instrumental variables and two-stage models. ACM Transactions on Software Engineering and Methodology 33 8 (2024) 1\u201331.","DOI":"10.1145\/3674730"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"David\u00a0A Grimes and Kenneth\u00a0F Schulz. 2002. Bias and causal associations in observational research. The lancet 359 9302 (2002) 248\u2013252.","DOI":"10.1016\/S0140-6736(02)07451-2"},{"key":"e_1_3_3_2_13_2","volume-title":"Using propensity scores in quasi-experimental designs","author":"Holmes William\u00a0M","year":"2013","unstructured":"William\u00a0M Holmes. 2013. Using propensity scores in quasi-experimental designs. Sage Publications."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139025751"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Masao Iwagami and Tomohiro Shinozaki. 2022. Introduction to matching in case-control and cohort studies. Annals of Clinical Epidemiology 4 2 (2022) 33\u201340.","DOI":"10.37737\/ace.22005"},{"key":"e_1_3_3_2_16_2","unstructured":"Natalia Juristo. 2018. Use and Misuse of the term experiment in the software repositories research. (2018). 12th International Conference on Predictive Models and Data Analytics in Software Engineering (PROMISE)."},{"key":"e_1_3_3_2_17_2","volume-title":"Basics of software engineering experimentation","author":"Juristo Natalia","year":"2013","unstructured":"Natalia Juristo and Ana\u00a0M Moreno. 2013. Basics of software engineering experimentation. Springer Science & Business Media."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Chris\u00a0F Kemerer and Sandra\u00a0A Slaughter. 1997. Determinants of software maintenance profiles: an empirical investigation. Journal of Software Maintenance: Research and Practice 9 4 (1997) 235\u2013251.","DOI":"10.1002\/(SICI)1096-908X(199707\/08)9:4<235::AID-SMR153>3.0.CO;2-3"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Foutse Khomh Massimiliano\u00a0Di Penta Yann-Ga\u00ebl Gu\u00e9h\u00e9neuc and Giuliano Antoniol. 2012. An Exploratory Study of the Impact of Antipatterns on Class Change- and Fault-Proneness. Empirical Softw. Engg. 17 3 (2012) 243\u2013275.","DOI":"10.1007\/s10664-011-9171-y"},{"key":"e_1_3_3_2_20_2","volume-title":"Modern epidemiology (fourth edition. ed.)","author":"Lash Timothy\u00a0L","year":"2021","unstructured":"Timothy\u00a0L Lash, Tyler\u00a0J VanderWeele, Sebastien Haneause, and Kenneth Rothman. 2021. Modern epidemiology (fourth edition. ed.). Wolters Kluwer, Philadelphia."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3345629.3345630"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Ariel Linden. 2015. Graphical displays for assessing covariate balance in matching studies. Journal of Evaluation in Clinical Practice 21 2 (2015) 242\u2013247.","DOI":"10.1111\/jep.12297"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/APSEC53868.2021.00031"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3143434.3143445"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.2003.1235447"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107587991"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.6084\/m9.figshare.30391231"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3744916.3787786"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696630.3731619"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR66628.2025.00027"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.2010.5609564"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1002\/9781444316568.wiem02059"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Fabio Palomba Gabriele Bavota Massimiliano\u00a0Di Penta Fausto Fasano Rocco Oliveto and Andrea\u00a0De Lucia. 2018. On the diffuseness and the impact on maintainability of code smells: a large scale empirical investigation. Empirical Software Engineering 23 (2018) 1188\u20131221.","DOI":"10.1007\/s10664-017-9535-z"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2009.5070551"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Paul\u00a0R Rosenbaum. 1989. Optimal matching for observational studies. J. Amer. Statist. Assoc. 84 408 (1989) 1024\u20131032.","DOI":"10.1080\/01621459.1989.10478868"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3692-2"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-1213-8"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Paul\u00a0R Rosenbaum. 2020. Modern algorithms for matching in observational studies. Annual Review of Statistics and Its Application 7 1 (2020) 143\u2013176.","DOI":"10.1146\/annurev-statistics-031219-041058"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Paul\u00a0R Rosenbaum and Donald\u00a0B Rubin. 1985. Constructing a control group using multivariate matched sampling methods that incorporate the propensity score. The American Statistician 39 1 (1985) 33\u201338.","DOI":"10.1080\/00031305.1985.10479383"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Donald\u00a0B Rubin. 1980. Bias reduction using Mahalanobis-metric matching. Biometrics (1980) 293\u2013298.","DOI":"10.2307\/2529981"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511810725"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3382494.3422160"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Nyyti Saarim\u00e4ki Mikel Robredo Valentina Lenarduzzi Sira Vegas Natalia Juristo and Davide Taibi. 2025. Does microservice adoption impact the velocity? A cohort study. Empirical Software Engineering 30 5 (2025) 130.","DOI":"10.1007\/s10664-025-10673-7"},{"key":"e_1_3_3_2_44_2","first-page":"569","volume-title":"Proceedings of the 21st International Conference on Mining Software Repositories","author":"Saarimaki Nyyti","year":"2024","unstructured":"Nyyti Saarimaki, Sira Vegas, Valentina Lenarduzzi, Davide Taibi, and Mikel Robredo. 2024. Cohort studies for mining software repositories. In Proceedings of the 21st International Conference on Mining Software Repositories. 569\u2013570."},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Elizabeth\u00a0A Stuart. 2010. Matching methods for causal inference: A review and a look forward. Statistical science: a review journal of the Institute of Mathematical Statistics 25 1 (2010) 1.","DOI":"10.1214\/09-STS313"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Felix\u00a0J Thoemmes and Eun\u00a0Sook Kim. 2011. A systematic review of propensity score methods in the social sciences. Multivariate behavioral research 46 1 (2011) 90\u2013118.","DOI":"10.1080\/00273171.2011.540475"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ESEM.2017.59"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Michele Tufano Fabio Palomba Gabriele Bavota Rocco Oliveto Massimiliano Di\u00a0Penta Andrea De\u00a0Lucia and Dennis Poshyvanyk. 2017. When and Why Your Code Starts to Smell Bad (and Whether the Smells Go Away). IEEE Transactions on Software Engineering 43 11 (2017) 1063\u20131088.","DOI":"10.1109\/TSE.2017.2653105"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Daniel Westreich and Stephen\u00a0R Cole. 2010. Invited commentary: positivity in practice. American journal of epidemiology 171 6 (2010) 674\u2013677.","DOI":"10.1093\/aje\/kwp436"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"crossref","unstructured":"TL Zakrison PC Austin and VA McCredie. 2018. A systematic review of propensity score methods in the acute care surgery literature: avoiding the pitfalls and proposing a set of reporting guidelines. European Journal of Trauma and Emergency Surgery 44 3 (2018) 385\u2013395.","DOI":"10.1007\/s00068-017-0786-6"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1201\/9781003102670"}],"event":{"name":"MSR '26: 23rd International Conference on Mining Software Repositories","location":"Rio de Janeiro Brazil","acronym":"MSR '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 23rd International Conference on Mining Software Repositories"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793302.3793378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:43:58Z","timestamp":1785494638000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793302.3793378"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":50,"alternative-id":["10.1145\/3793302.3793378","10.1145\/3793302"],"URL":"https:\/\/doi.org\/10.1145\/3793302.3793378","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}