{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:30:27Z","timestamp":1757622627257,"version":"3.44.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030865191"},{"type":"electronic","value":"9783030865207"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86520-7_48","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T15:25:48Z","timestamp":1631201148000},"page":"781-795","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Sibling Regression for Generalized Linear Models"],"prefix":"10.1007","author":[{"given":"Shiv","family":"Shankar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Sheldon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,10]]},"reference":[{"key":"48_CR1","unstructured":"Adams, R., Ji, Y., Wang, X., Saria, S.: Learning models from data with measurement error: tackling underreporting. arXiv:1901.09060 (2019)"},{"key":"48_CR2","doi-asserted-by":"publisher","first-page":"7353","DOI":"10.1073\/pnas.1510489113","volume":"113","author":"S Athey","year":"2016","unstructured":"Athey, S., Imbens, G.: Recursive partitioning for heterogeneous causal effects. Proc. Nat. Acad. Sci. 113, 7353\u20137360 (2016)","journal-title":"Proc. Nat. Acad. Sci."},{"key":"48_CR3","doi-asserted-by":"crossref","unstructured":"Bang, H., Robins, J.: Doubly robust estimation in missing data and causal inference models. Biometrics 61, 962\u2013973 (2005)","DOI":"10.1111\/j.1541-0420.2005.00377.x"},{"key":"48_CR4","unstructured":"Belsley, D.A., Kuh, E., Welsch, R.E.: Regression Diagnostics: Identifying Influential Data and Sources of Collinearity, vol. 571. John Wiley & Sons, Hoboken (2005)"},{"key":"48_CR5","unstructured":"Chouldechova, A., Benavides-Prado, D., Fialko, O., Vaithianathan. R.: A case study of algorithm-assisted decision making in child maltreatment hotline screening decisions. In: Proceedings of the 1st Conference on Fairness, Accountability and Transparency, volume 81 of Proceedings of Machine Learning Research, pp. 134\u2013148. PMLR (2018)"},{"key":"48_CR6","doi-asserted-by":"crossref","unstructured":"Davidson, T., Bhattacharya, D., Weber, I.: Racial bias in hate speech and abusive language detection datasets. In: Workshop on Abusive Language Online (2019)","DOI":"10.18653\/v1\/W19-3504"},{"issue":"2","key":"48_CR7","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1177\/096228029600500205","volume":"5","author":"AK Formann","year":"1996","unstructured":"Formann, A.K., Kohlmann, T.: Latent class analysis in medical research. Statist. Methods Med. Res. 5(2), 179\u2013211 (1996)","journal-title":"Statist. Methods Med. Res."},{"key":"48_CR8","doi-asserted-by":"crossref","unstructured":"Genb\u00e4ck, M., de Luna, X.: Causal inference accounting for unobserved confounding after outcome regression and doubly robust estimation. Biometrics 75(2), 506\u2013515 (2019)","DOI":"10.1111\/biom.13001"},{"issue":"1","key":"48_CR9","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/096228029900800104","volume":"8","author":"NJ Horton","year":"1999","unstructured":"Horton, N.J., Laird, N.M.: Maximum likelihood analysis of generalized linear models with missing covariates. Statist. Methods Med. Res. 8(1), 37\u201350 (1999)","journal-title":"Statist. Methods Med. Res."},{"key":"48_CR10","doi-asserted-by":"crossref","unstructured":"Hutchinson, R.A., He, L., Emerson, S.C.: Species distribution modeling of citizen science data as a classification problem with class-conditional noise. In: AAAI, pp. 4516\u20134523 (2017)","DOI":"10.1609\/aaai.v31i1.11177"},{"key":"48_CR11","doi-asserted-by":"crossref","unstructured":"Ibrahim, J.G., Weisberg, S.: Incomplete data in generalized linear models with continuous covariates. Australia J. Statist. 34(3), 461\u2013470 (1992)","DOI":"10.1111\/j.1467-842X.1992.tb01062.x"},{"key":"48_CR12","doi-asserted-by":"crossref","unstructured":"Ibrahim, J.G., Lipsitz, S.R., Chen, M.-H.: Missing covariates in generalized linear models when the missing data mechanism is non-ignorable. J. R. Statist. Soc. Ser. B (Statist. Methodol.) 61(1), 173\u2013190 (1999)","DOI":"10.1111\/1467-9868.00170"},{"issue":"433","key":"48_CR13","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1080\/01621459.1996.10476680","volume":"91","author":"MP Jones","year":"1996","unstructured":"Jones, M.P.: Indicator and stratification methods for missing explanatory variables in multiple linear regression. J. Am. statist. Assoc. 91(433), 222\u2013230 (1996)","journal-title":"J. Am. statist. Assoc."},{"issue":"2","key":"48_CR14","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1111\/2041-210X.12507","volume":"7","author":"J Knape","year":"2016","unstructured":"Knape, J., Korner-Nievergelt, F.: On assumptions behind estimates of abundance from counts at multiple sites. Methods Ecol. Evol. 7(2), 206\u2013209 (2016)","journal-title":"Methods Ecol. Evol."},{"key":"48_CR15","unstructured":"Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Technique. MIT Press, Cambridge (2009)"},{"key":"48_CR16","doi-asserted-by":"crossref","unstructured":"Kupperman, M.: Probabilities of hypotheses and information-statistics in sampling from exponential-class populations. Ann. Math. Statist. 29(2), 571\u2013575 (1958). ISSN 00034851. http:\/\/www.jstor.org\/stable\/2237349","DOI":"10.1214\/aoms\/1177706633"},{"issue":"1","key":"48_CR17","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1093\/jpe\/rtr042","volume":"5","author":"SR Lele","year":"2012","unstructured":"Lele, S.R., Moreno, M., Bayne, E.: Dealing with detection error in site occupancy surveys: what can we do with a single survey? J. Plant Ecol. 5(1), 22\u201331 (2012)","journal-title":"J. Plant Ecol."},{"issue":"420","key":"48_CR18","first-page":"1227","volume":"87","author":"RJ Little","year":"1992","unstructured":"Little, R.J.: Regression with missing x\u2019s: a review. J. Am. Statist. Assoc. 87(420), 1227\u20131237 (1992)","journal-title":"J. Am. Statist. Assoc."},{"issue":"8","key":"48_CR19","doi-asserted-by":"publisher","first-page":"2248","DOI":"10.1890\/0012-9658(2002)083[2248:ESORWD]2.0.CO;2","volume":"83","author":"DI MacKenzie","year":"2002","unstructured":"MacKenzie, D.I., Nichols, J.D., Lachman, G.B., Droege, S., Royle, A., Langtimm, C.A.: Estimating site occupancy rates when detection probabilities are less than one. Ecology 83(8), 2248\u20132255 (2002)","journal-title":"Ecology"},{"key":"48_CR20","unstructured":"Menon, A., van Rooyen, B., Ong, C., Williamson, R.: Learning from corrupted binary labels via class-probability estimation. Journal Machine Learning Research, vol. 16 (2015)"},{"key":"48_CR21","unstructured":"Natarajan, N., Dhillon, I., Ravikumar, P., Tewari, A.: Learning with noisy labels. In: Advances in Neural Information Processing Systems (2013)"},{"key":"48_CR22","doi-asserted-by":"crossref","unstructured":"Nelder, J., Wedderburn, R.: Generalized linear models. J. R. Statist. Soc. 135(3), 370\u2013384 (1972)","DOI":"10.2307\/2344614"},{"key":"48_CR23","doi-asserted-by":"crossref","unstructured":"Olteanu, A., Castillo, C., Diaz, F., Kiciman, E.: Social data: biases, methodological pitfalls, and ethical boundaries. CoRR (2016)","DOI":"10.2139\/ssrn.2886526"},{"key":"48_CR24","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1016\/0898-1221(87)90236-7","volume":"14","author":"J Robins","year":"1987","unstructured":"Robins, J., Morgenstern, H.: The foundations of confounding in epidemiology. Comput. Math. Appl. 14, 869\u2013916 (1987)","journal-title":"Comput. Math. Appl."},{"issue":"1","key":"48_CR25","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1111\/j.0006-341X.2004.00142.x","volume":"60","author":"JA Royle","year":"2004","unstructured":"Royle, J.A.: N-Mixture models for estimating population size from spatially replicated counts. Biometrics 60(1), 108\u2013115 (2004)","journal-title":"Biometrics"},{"key":"48_CR26","unstructured":"Sch\u00f6lkopf, B., et al.: Removing systematic errors for exoplanet search via latent causes. In: Proceedings of the 32nd International Conference on Machine Learning (ICML) (2015)"},{"key":"48_CR27","unstructured":"Serv\u00e9n, D., Brummitt, C.: pygam: Generalized additive models in python, March 2018. https:\/\/doi.org\/10.5281\/zenodo.1208723"},{"key":"48_CR28","doi-asserted-by":"publisher","unstructured":"Shankar, S., Sheldon, D., Sun, T., Pickering, J., Dietterich, T.: Three-quarter sibling regression for denoising observational data, pp. 5960\u20135966 (2019). https:\/\/doi.org\/10.24963\/ijcai.2019\/826","DOI":"10.24963\/ijcai.2019\/826"},{"key":"48_CR29","unstructured":"Sharma, A.: Necessary and probably sufficient test for finding valid instrumental variables. CoRR, abs\/1812.01412 (2018)"},{"issue":"2","key":"48_CR30","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1111\/2041-210X.12432","volume":"7","author":"P S\u00f3lymos","year":"2016","unstructured":"S\u00f3lymos, P., Lele, S.R.: Revisiting resource selection probability functions and single-visit methods: clarification and extensions. Methods Ecol. Evol. 7(2), 196\u2013205 (2016)","journal-title":"Methods Ecol. Evol."},{"key":"48_CR31","doi-asserted-by":"publisher","unstructured":"White, H.: Estimation, Inference and Specification Analysis. Econometric Society Monographs. Cambridge University Press, Cambridge (1994). https:\/\/doi.org\/10.1017\/CCOL0521252806","DOI":"10.1017\/CCOL0521252806"},{"key":"48_CR32","doi-asserted-by":"crossref","unstructured":"Yu, J., Hutchinson, R.A., Wong, W.-K.: A latent variable model for discovering bird species commonly misidentified by citizen scientists. In: Twenty-Eighth AAAI Conference on Artificial Intelligence (2014)","DOI":"10.1609\/aaai.v28i1.8763"},{"key":"48_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Jenkins, D., Manimaran, S., Johnson, W.: Alternative empirical bayes models for adjusting for batch effects in genomic studies. BMC Bioinformatics, vol. 19 (2018)","DOI":"10.1186\/s12859-018-2263-6"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86520-7_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:04:45Z","timestamp":1757369085000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86520-7_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030865191","9783030865207"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86520-7_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"10 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","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":"869","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":"210","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":"24% - 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":"3-4","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":"3-9","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)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}