{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T02:29:51Z","timestamp":1782959391261,"version":"3.54.5"},"update-to":[{"DOI":"10.1371\/journal.pgen.1010107","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T00:00:00Z","timestamp":1648512000000}}],"reference-count":49,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T00:00:00Z","timestamp":1647475200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81773547"],"award-info":[{"award-number":["81773547"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shandong Provincial Natural Science Foundation of China","award":["ZR2019ZD02"],"award-info":[{"award-number":["ZR2019ZD02"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82003557"],"award-info":[{"award-number":["82003557"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shandong Provincial Key Research and Development project","award":["2018CXGC1210"],"award-info":[{"award-number":["2018CXGC1210"]}]}],"content-domain":{"domain":["www.plosgenetics.org"],"crossmark-restriction":false},"short-container-title":["PLoS Genet"],"abstract":"<jats:p>Nonrandom selection in one-sample Mendelian Randomization (MR) results in biased estimates and inflated type I error rates only when the selection effects are sufficiently large. In two-sample MR, the different selection mechanisms in two samples may more seriously affect the causal effect estimation. Firstly, we propose sufficient conditions for causal effect invariance under different selection mechanisms using two-sample MR methods. In the simulation study, we consider 49 possible selection mechanisms in two-sample MR, which depend on genetic variants (<jats:italic>G<\/jats:italic>), exposures (<jats:italic>X<\/jats:italic>), outcomes (<jats:italic>Y<\/jats:italic>) and their combination. We further compare eight pleiotropy-robust methods under different selection mechanisms. Results of simulation reveal that nonrandom selection in sample II has a larger influence on biases and type I error rates than those in sample I. Furthermore, selections depending on<jats:italic>X+Y<\/jats:italic>,<jats:italic>G+Y<\/jats:italic>, or<jats:italic>G+X+Y<\/jats:italic>in sample II lead to larger biases than other selection mechanisms. Notably, when selection depends on<jats:italic>Y<\/jats:italic>, bias of causal estimation for non-zero causal effect is larger than that for null causal effect. Especially, the mode based estimate has the largest standard errors among the eight methods. In the absence of pleiotropy, selections depending on<jats:italic>Y<\/jats:italic>or<jats:italic>G<\/jats:italic>in sample II show nearly unbiased causal effect estimations when the casual effect is null. In the scenarios of balanced pleiotropy, all eight MR methods, especially MR-Egger, demonstrate large biases because the nonrandom selections result in the violation of the Instrument Strength Independent of Direct Effect (InSIDE) assumption. When directional pleiotropy exists, nonrandom selections have a severe impact on the eight MR methods. Application demonstrates that the nonrandom selection in sample II (coronary heart disease patients) can magnify the causal effect estimation of obesity on HbA1c levels. In conclusion, nonrandom selection in two-sample MR exacerbates the bias of causal effect estimation for pleiotropy-robust MR methods.<\/jats:p>","DOI":"10.1371\/journal.pgen.1010107","type":"journal-article","created":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T18:52:32Z","timestamp":1647543152000},"page":"e1010107","update-policy":"https:\/\/doi.org\/10.1371\/journal.pgen.corrections_policy","source":"Crossref","is-referenced-by-count":9,"title":["Impact of nonrandom selection mechanisms on the causal effect estimation for two-sample Mendelian randomization methods"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6304-0817","authenticated-orcid":true,"given":"Yuanyuan","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5636-4028","authenticated-orcid":true,"given":"Lei","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8566-9552","authenticated-orcid":true,"given":"Xu","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoru","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7894-1172","authenticated-orcid":true,"given":"Xinhui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3317-1960","authenticated-orcid":true,"given":"Yifan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3527-4488","authenticated-orcid":true,"given":"Zhongshang","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongkai","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0378-7956","authenticated-orcid":true,"given":"Fuzhong","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,3,17]]},"reference":[{"key":"pgen.1010107.ref001","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1093\/ije\/dyh132","article-title":"Mendelian randomization: prospects, potentials, and limitations","volume":"33","author":"GD Smith","year":"2004","journal-title":"Int J Epidemiol"},{"key":"pgen.1010107.ref002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/ije\/dyg070","article-title":"\u2019Mendelian randomization\u2019: can genetic epidemiology contribute to understanding environmental determinants of disease?","volume":"32","author":"GD Smith","year":"2003","journal-title":"Int J Epidemiol"},{"key":"pgen.1010107.ref003","doi-asserted-by":"crossref","first-page":"R89","DOI":"10.1093\/hmg\/ddu328","article-title":"Mendelian randomization: genetic anchors for causal inference in epidemiological studies","volume":"23","author":"G Davey Smith","year":"2014","journal-title":"Hum Mol Genet"},{"key":"pgen.1010107.ref004","article-title":"Genetic epidemiology and Mendelian randomization for informing disease therapeutics: Conceptual and methodological challenges","author":"L Paternoster","year":"2017","journal-title":"PLoS Genet"},{"key":"pgen.1010107.ref005","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/978-1-4939-7868-7_13","article-title":"A primer in mendelian randomization methodology with a focus on utilizing published summary association data","volume":"1793","author":"NL Dimou","year":"2018","journal-title":"Methods Mol Biol"},{"key":"pgen.1010107.ref006","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1093\/ije\/dyy262","article-title":"An examination of multivariable Mendelian randomization in the single-sample and two-sample summary data settings","volume":"48","author":"E Sanderson","year":"2019","journal-title":"Int J Epidemiol"},{"key":"pgen.1010107.ref007","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1097\/EDE.0000000000000972","article-title":"Selection bias when estimating average treatment effects using one-sample instrumental variable analysis","volume":"30","author":"RA Hughes","year":"2019","journal-title":"Epidemiology"},{"key":"pgen.1010107.ref008","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1093\/ije\/dyx206","article-title":"Collider scope: when selection bias can substantially influence observed associations","volume":"47","author":"MR Munaf\u00f2","year":"2018","journal-title":"Int J Epidemiol"},{"key":"pgen.1010107.ref009","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1093\/ije\/dyv080","article-title":"Mendelian randomization with invalid instruments: effect estimation and bias detection through Egger regression","volume":"44","author":"J Bowden","year":"2015","journal-title":"Int J Epidemiol"},{"key":"pgen.1010107.ref010","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1002\/gepi.21965","article-title":"Consistent estimation in mendelian randomization with some invalid instruments using a weighted median estimator","volume":"40","author":"J Bowden","year":"2016","journal-title":"Genet Epidemiol"},{"key":"pgen.1010107.ref011","doi-asserted-by":"crossref","first-page":"947","DOI":"10.1007\/s10654-018-0424-6","article-title":"Mendelian randomization with a binary exposure variable: interpretation and presentation of causal estimates","volume":"33","author":"S Burgess","year":"2018","journal-title":"Eur J Epidemiol"},{"key":"pgen.1010107.ref012","article-title":"Robust instrumental variable methods using multiple candidate instruments with application to Mendelian randomization","author":"S Burgess","year":"2018","journal-title":"arXiv:1606.03729v2"},{"key":"pgen.1010107.ref013","doi-asserted-by":"crossref","first-page":"2333","DOI":"10.1177\/0962280215597579","article-title":"A review of instrumental variable estimators for Mendelian randomization","volume":"26","author":"S Burgess","year":"2017","journal-title":"Stat Methods Med Res"},{"key":"pgen.1010107.ref014","doi-asserted-by":"crossref","first-page":"1985","DOI":"10.1093\/ije\/dyx102","article-title":"Robust inference in summary data Mendelian randomization via the zero modal pleiotropy assumption","volume":"46","author":"FP Hartwig","year":"2017","journal-title":"Int J Epidemiol"},{"key":"pgen.1010107.ref015","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1038\/s41467-019-14156-4","article-title":"A robust and efficient method for Mendelian randomization with hundreds of genetic variants","volume":"11","author":"S Burgess","year":"2020","journal-title":"Nat Commun"},{"key":"pgen.1010107.ref016","doi-asserted-by":"crossref","first-page":"1742","DOI":"10.1214\/19-AOS1866","article-title":"Statistical inference in two-sample summary-data mendelian randomization using robust adjusted profile score","volume":"48","author":"Q Zhao","year":"2020","journal-title":"Ann Stat"},{"key":"pgen.1010107.ref017","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1002\/gepi.21998","article-title":"Bias due to participant overlap in two-sample Mendelian randomization","volume":"40","author":"S Burgess","year":"2016","journal-title":"Genet Epidemiol"},{"key":"pgen.1010107.ref018","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1002\/gepi.22077","article-title":"Mendelian randomization with fine-mapped genetic data: Choosing from large numbers of correlated instrumental variables","volume":"41","author":"S Burgess","year":"2017","journal-title":"Genet Epidemiol"},{"key":"pgen.1010107.ref019","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1111\/j.2517-6161.1995.tb02029.x","article-title":"Collapsibility of logistic-regression coefficients","volume":"57","author":"JH Guo","year":"1995","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"pgen.1010107.ref020","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1214\/10-STS340","article-title":"Graphical models for inference under outcome-dependent sampling","volume":"25","author":"V Didelez","year":"2010","journal-title":"Stat Sci"},{"key":"pgen.1010107.ref021","doi-asserted-by":"crossref","first-page":"R195","DOI":"10.1093\/hmg\/ddy163","article-title":"Evaluating the potential role of pleiotropy in Mendelian randomization studies","volume":"27","author":"G Hemani","year":"2018","journal-title":"Hum Mol Genet"},{"key":"pgen.1010107.ref022","doi-asserted-by":"crossref","first-page":"1339","DOI":"10.1080\/01621459.2018.1498346","article-title":"On the use of the lasso for instrumental variables estimation with some invalid instruments","volume":"114","author":"F Windmeijer","year":"2018","journal-title":"J Am Stat Assoc"},{"key":"pgen.1010107.ref023","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1186\/s12906-017-1817-x","article-title":"Prevalence and predictors of complementary and alternative medicine use among people with coronary heart disease or at risk for this in the sixth Troms\u00f8 study: a comparative analysis using protection motivation theory","volume":"17","author":"AE Kristoffersen","year":"2017","journal-title":"BMC Complement Altern Med"},{"key":"pgen.1010107.ref024","article-title":"Exploring the causal pathway from body mass index to coronary heart disease: a network Mendelian randomization study","author":"X Hu","year":"2020","journal-title":"Ther Adv Chronic Dis"},{"key":"pgen.1010107.ref025","doi-asserted-by":"crossref","first-page":"1991","DOI":"10.2337\/dc18-0289","article-title":"The Impact of Glycated Hemoglobin (HbA1c) on Cardiovascular Disease Risk: A Mendelian Randomization Study Using UK Biobank","volume":"41","author":"SL Au Yeung","year":"2018","journal-title":"Diabetes Care"},{"key":"pgen.1010107.ref026","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1001\/jama.2016.21042","article-title":"Genetic Association of Waist-to-Hip Ratio with Cardiometabolic Traits, Type 2 Diabetes, and Coronary Heart Disease.","volume":"317","author":"CA Emdin","year":"2017","journal-title":"JAMA"},{"key":"pgen.1010107.ref027","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1038\/nature14177","article-title":"Genetic studies of body mass index yield new insights for obesity biology","volume":"518","author":"AE Locke","year":"2015","journal-title":"Nature"},{"key":"pgen.1010107.ref028","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1038\/nature14132","article-title":"New genetic loci link adipose and insulin biology to body fat distribution","volume":"518","author":"D Shungin","year":"2015","journal-title":"Nature"},{"key":"pgen.1010107.ref029","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41586-018-0579-z","article-title":"The UK biobank resource with deep phenotyping and genomic data","volume":"562","author":"C Bycroft","year":"2018","journal-title":"Nature"},{"key":"pgen.1010107.ref030","doi-asserted-by":"crossref","first-page":"1639","DOI":"10.1093\/ije\/dyaa266","article-title":"Bias in two-sample Mendelian randomization when using heritable covariable-adjusted summary associations","volume":"50","author":"FP Hartwig","year":"2021","journal-title":"Int J Epidemiol."},{"key":"pgen.1010107.ref031","article-title":"Causal diagrams and three pairs of biases. Lunet N","author":"E Shahar","journal-title":"Epidemiology\u2013Current Perspectives on Research and Practice"},{"key":"pgen.1010107.ref032","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1097\/EDE.0000000000001072","article-title":"Survival bias in mendelian randomization studies a threat to causal inference","volume":"30","author":"RAJ Smit","year":"2019","journal-title":"Epidemiology"},{"key":"pgen.1010107.ref033","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1093\/ije\/dyy202","article-title":"Contextualizing selection bias in Mendelian randomization: how bad is it likely to be?","volume":"48","author":"A Gkatzionis","year":"2019","journal-title":"Int J Epidemiol"},{"key":"pgen.1010107.ref034","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1097\/EDE.0000000000000409","article-title":"Selection bias due to loss to follow up in cohort studies","volume":"27","author":"CJ Howe","year":"2016","journal-title":"Epidemiology"},{"key":"pgen.1010107.ref035","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1097\/EDE.0000000000000699","article-title":"Nature as a Trialist?: Deconstructing the Analogy Between Mendelian Randomization and Randomized Trials","volume":"28","author":"SA Swanson","year":"2017","journal-title":"Epidemiology"},{"key":"pgen.1010107.ref036","doi-asserted-by":"crossref","first-page":"R170","DOI":"10.1093\/hmg\/ddz204","article-title":"Within family Mendelian randomization studies","volume":"28","author":"NM Davies","year":"2019","journal-title":"Hum Mol Genet"},{"key":"pgen.1010107.ref037","doi-asserted-by":"crossref","first-page":"3519","DOI":"10.1038\/s41467-020-17117-4","article-title":"Avoiding dynastic, assortative mating, and population stratification biases in mendelian randomization through within-family analyses","volume":"11","author":"B Brumpton","year":"2020","journal-title":"Nat Commun"},{"key":"pgen.1010107.ref038","doi-asserted-by":"crossref","first-page":"1814","DOI":"10.1093\/ije\/dyx131","article-title":"Body mass index and breast cancer survival: a mendelian randomization analysis","volume":"46","author":"Q Guo","year":"2017","journal-title":"Int J Epidemiol"},{"key":"pgen.1010107.ref039","doi-asserted-by":"crossref","first-page":"534","DOI":"10.1016\/S2213-8587(17)30096-7","article-title":"Relations between lipoprotein(a) concentrations, lpa genetic variants, and the risk of mortality in patients with established coronary heart disease: a molecular and genetic association study","volume":"5","author":"S Zewinger","year":"2017","journal-title":"Lancet Diabetes Endo"},{"key":"pgen.1010107.ref040","doi-asserted-by":"crossref","first-page":"1967","DOI":"10.1158\/1055-9965.EPI-05-0196","article-title":"Alcohol, ALDH2, and esophageal cancer: a meta-analysis which illustrates the potentials and limitations of a Mendelian randomization approach","volume":"14","author":"SJ Lewis","year":"2005","journal-title":"Cancer Epidemiol Biomarkers Prev"},{"key":"pgen.1010107.ref041","doi-asserted-by":"crossref","first-page":"660212","DOI":"10.3389\/fneur.2021.660212","article-title":"Mendelian randomization of dyslipidemia on cognitive Impairment among older americans","volume":"12","author":"M Fu","year":"2021","journal-title":"Front Neurol"},{"issue":"2","key":"pgen.1010107.ref042","first-page":"369","article-title":"Do Gametes Woo? Evidence for Their Nonrandom Union at Fertilization","volume":"207","author":"JH Nadeau","year":"2017","journal-title":"Genetics"},{"key":"pgen.1010107.ref043","doi-asserted-by":"crossref","first-page":"678","DOI":"10.1002\/sim.4138","article-title":"Mendelian randomization analysis of case-control data using structural mean models","volume":"30","author":"J Bowden","year":"2011","journal-title":"Stat Med"},{"key":"pgen.1010107.ref044","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1111\/biom.13166","article-title":"On Mendelian randomization analysis of case-control study","volume":"76","author":"H Zhang","year":"2020","journal-title":"Biometrics"},{"key":"pgen.1010107.ref045","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1097\/EDE.0000000000000639","article-title":"Instrumental Variable Analyses and Selection Bias","volume":"28","author":"C Canan","year":"2017","journal-title":"Epidemiology"},{"key":"pgen.1010107.ref046","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1097\/EDE.0000000000000973","article-title":"A Practical Guide to Selection Bias in Instrumental Variable Analyses","volume":"30","author":"SA Swanson","year":"2019","journal-title":"Epidemiology"},{"key":"pgen.1010107.ref047","doi-asserted-by":"crossref","first-page":"107382","DOI":"10.1016\/j.csda.2021.107382","article-title":"Correcting for sample selection bias in Bayesian distributional regression models","volume":"168","author":"PFV Wiemann","year":"2022","journal-title":"Comput Stat Data Anal"},{"key":"pgen.1010107.ref048","volume-title":"Bayesian approach for selection bias correction in regression","author":"L. Mokatrin","year":"2011"},{"key":"pgen.1010107.ref049","unstructured":"Bareinboim E, Pearl J. Controlling selection bias in causal inference. In Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS). La Palma, Canary Islands, 2012;100\u2013108"}],"updated-by":[{"DOI":"10.1371\/journal.pgen.1010107","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T00:00:00Z","timestamp":1648512000000}}],"container-title":["PLOS Genetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pgen.1010107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T13:53:52Z","timestamp":1726840432000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pgen.1010107"}},"subtitle":[],"editor":[{"given":"Caroline","family":"Relton","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,3,17]]},"references-count":49,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,3,17]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pgen.1010107","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pgen.1010107","asserted-by":"object"}]},"ISSN":["1553-7404"],"issn-type":[{"value":"1553-7404","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,17]]}}}