{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T23:57:35Z","timestamp":1771631855923,"version":"3.50.1"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030336066","type":"print"},{"value":"9783030336073","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-33607-3_12","type":"book-chapter","created":{"date-parts":[[2019,11,7]],"date-time":"2019-11-07T00:05:28Z","timestamp":1573085128000},"page":"102-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["The Prevalence of Errors in Machine Learning Experiments"],"prefix":"10.1007","author":[{"given":"Martin","family":"Shepperd","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahir","family":"Arzoky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Capiluppi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Counsell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giuseppe","family":"Destefanis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Swift","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Allan","family":"Tucker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leila","family":"Yousefi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,18]]},"reference":[{"issue":"1","key":"12_CR1","first-page":"2653","volume":"18","author":"A Benavoli","year":"2017","unstructured":"Benavoli, A., Corani, G., Dem\u0161ar, J., Zaffalon, M.: Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysis. J. Mach. Learn. Res. 18(1), 2653\u20132688 (2017)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"12_CR2","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/S0895-4356(00)00314-0","volume":"54","author":"R Bender","year":"2001","unstructured":"Bender, R., Lange, S.: Adjusting for multiple testing - when and how? J. Clin. Epidemiol. 54(4), 343\u2013349 (2001)","journal-title":"J. Clin. Epidemiol."},{"issue":"1","key":"12_CR3","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","volume":"57","author":"Y Benjamini","year":"1995","unstructured":"Benjamini, Y., Hochberg, Y.: Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. Royal Stat. Soc.: Ser. B (Methodol.) 57(1), 289\u2013300 (1995)","journal-title":"J. Royal Stat. Soc.: Ser. B (Methodol.)"},{"issue":"2","key":"12_CR4","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/s10515-013-0129-8","volume":"21","author":"D Bowes","year":"2014","unstructured":"Bowes, D., Hall, T., Gray, D.: DConfusion: a technique to allow cross study performance evaluation of fault prediction studies. Autom. Softw. Eng. 21(2), 287\u2013313 (2014)","journal-title":"Autom. Softw. Eng."},{"issue":"4","key":"12_CR5","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1177\/1948550616673876","volume":"8","author":"N Brown","year":"2017","unstructured":"Brown, N., Heathers, J.: The GRIM test: a simple technique detects numerous anomalies in the reporting of results in psychology. Soc. Psychol. Pers. Sci. 8(4), 363\u2013369 (2017)","journal-title":"Soc. Psychol. Pers. Sci."},{"issue":"4","key":"12_CR6","doi-asserted-by":"publisher","first-page":"7346","DOI":"10.1016\/j.eswa.2008.10.027","volume":"36","author":"C Catal","year":"2009","unstructured":"Catal, C., Diri, B.: A systematic review of software fault prediction studies. Expert Syst. Appl. 36(4), 7346\u20137354 (2009)","journal-title":"Expert Syst. Appl."},{"key":"12_CR7","doi-asserted-by":"publisher","first-page":"140216","DOI":"10.1098\/rsos.140216","volume":"1","author":"D Colquhoun","year":"2014","unstructured":"Colquhoun, D.: An investigation of the false discovery rate and the misinterpretation of p-values. Royal Soc. Open Sci. 1, 140216 (2014)","journal-title":"Royal Soc. Open Sci."},{"key":"12_CR8","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1\u201330 (2006)","journal-title":"J. Mach. Learn. Res."},{"key":"12_CR9","doi-asserted-by":"publisher","first-page":"621","DOI":"10.3389\/fpsyg.2015.00621","volume":"6","author":"B Earp","year":"2015","unstructured":"Earp, B., Trafimow, D.: Replication, falsification, and the crisis of confidence in social psychology. Front. Psychol. 6, 621 (2015)","journal-title":"Front. Psychol."},{"issue":"6","key":"12_CR10","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1109\/TSE.2011.103","volume":"38","author":"T Hall","year":"2012","unstructured":"Hall, T., Beecham, S., Bowes, D., Gray, D., Counsell, S.: A systematic literature review on fault prediction performance in software engineering. IEEE Trans. Softw. Eng. 38(6), 1276\u20131304 (2012)","journal-title":"IEEE Trans. Softw. Eng."},{"issue":"8","key":"12_CR11","doi-asserted-by":"publisher","first-page":"e124","DOI":"10.1371\/journal.pmed.0020124","volume":"2","author":"J Ioannidis","year":"2005","unstructured":"Ioannidis, J.: Why most published research findings are false. PLoS Med. 2(8), e124 (2005)","journal-title":"PLoS Med."},{"key":"12_CR12","doi-asserted-by":"crossref","DOI":"10.1201\/b19467","volume-title":"Evidence-Based Software Engineering and Systematic Reviews","author":"B Kitchenham","year":"2015","unstructured":"Kitchenham, B., Budgen, D., Brereton, P.: Evidence-Based Software Engineering and Systematic Reviews. CRC Press, Boca Raton (2015)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Li, N., Shepperd, M., Guo, Y.: A systematic review of unsupervised learning techniques for software defect prediction. Inf. Softw. Technol. (2019, under review)","DOI":"10.1016\/j.infsof.2020.106287"},{"issue":"1","key":"12_CR14","doi-asserted-by":"publisher","first-page":"0021","DOI":"10.1038\/s41562-016-0021","volume":"1","author":"M Munaf\u00f2","year":"2017","unstructured":"Munaf\u00f2, M., et al.: A manifesto for reproducible science. Nat. Hum. Behav. 1(1), 0021 (2017)","journal-title":"Nat. Hum. Behav."},{"issue":"4","key":"12_CR15","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.3758\/s13428-015-0664-2","volume":"48","author":"M Nuijten","year":"2016","unstructured":"Nuijten, M., Hartgerink, C., van Assen, M., Epskamp, S., Wicherts, J.: The prevalence of statistical reporting errors in psychology (1985\u20132013). Behav. Res. Methods 48(4), 1205\u20131226 (2016)","journal-title":"Behav. Res. Methods"},{"issue":"1","key":"12_CR16","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/s11192-018-2750-6","volume":"116","author":"Marcelo S. Perlin","year":"2018","unstructured":"Perlin, M., Imasato, T., Borenstein, D.: Is predatory publishing a real threat? Evidence from a large database study. Scientometrics (2018, online). https:\/\/doi.org\/10.1007\/s11192-018-2750-6","journal-title":"Scientometrics"},{"issue":"6","key":"12_CR17","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.: Researcher bias: the use of machine learning in software defect prediction. IEEE Trans. Softw. Eng. 40(6), 603\u2013616 (2014)","journal-title":"IEEE Trans. Softw. Eng."}],"container-title":["Lecture Notes in Computer Science","Intelligent Data Engineering and Automated Learning \u2013 IDEAL 2019"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-33607-3_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T11:00:05Z","timestamp":1721991605000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-33607-3_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030336066","9783030336073"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-33607-3_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"18 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IDEAL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Data Engineering and Automated Learning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Manchester","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ideal2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.confercare.manchester.ac.uk\/events\/ideal2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Open","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"149","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"94","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"63% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}