{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:01:14Z","timestamp":1780498874205,"version":"3.54.1"},"reference-count":54,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["225790\/Z\/22\/Z"],"award-info":[{"award-number":["225790\/Z\/22\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"name":"United Kingdom Research"},{"name":"Innovation Medical Research Council","award":["MC_UU_00040\/01"],"award-info":[{"award-number":["MC_UU_00040\/01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,31]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>Nonlinear causal effects are prevalent in many research scenarios involving continuous exposures, and instrumental variables (IVs) can be employed to investigate such effects, particularly in the presence of unmeasured confounders. However, common IV methods for nonlinear effect analysis, such as IV regression or the control-function method, have inherent limitations, leading to either low statistical power or potentially misleading conclusions. In this work, we propose an alternative IV framework for nonlinear effect analysis, which has recently emerged in genetic epidemiology and addresses many of the drawbacks of existing IV methods. The proposed IV framework consists of up to three key \u201cS\u201d elements: (i) the Stratification approach, which constructs multiple strata that are sub-samples of the population in which the IV core assumptions remain valid, (ii) the Scalar-on-function model and Scalar-on-scalar model, which connect local stratum-specific information to global effect estimation, and (iii) the Sum-of-single-effects method for effect estimation. This framework enables study of the effect function while avoiding unnecessary model assumptions. In particular, it facilitates the identification of change points or threshold values in causal effects. Through a wide variety of simulations, we demonstrate that our framework outperforms other representative nonlinear IV methods in predicting the effect shape when the instrument is weak and can accurately estimate the effect function as well as identify the change point and predict its value under various structural model and effect shape scenarios. We further apply our framework to assess the nonlinear effect of alcohol consumption on systolic blood pressure using a genetic instrument (ie Mendelian randomization) with UK Biobank data. Our analysis detects a threshold beyond which alcohol intake exhibits a clear causal effect on the outcome. Our results are consistent with published medical guidelines.<\/jats:p>","DOI":"10.1093\/biostatistics\/kxaf043","type":"journal-article","created":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T12:46:27Z","timestamp":1761655587000},"source":"Crossref","is-referenced-by-count":3,"title":["Stratification-based instrumental variable analysis framework for nonlinear effect analysis"],"prefix":"10.1093","volume":"26","author":[{"given":"Haodong","family":"Tian","sequence":"first","affiliation":[{"name":"Center for Genomic Medicine, Massachusetts General Hospital, 185 Cambridge Street , Boston, MA 02114,","place":["United States"]},{"name":"Broad Institute of MIT and Harvard, 415 Main Street , Cambridge, MA 02142,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashish","family":"Patel","sequence":"additional","affiliation":[{"name":"MRC Biostatistics Unit, University of Cambridge, Robinson Way , Cambridge CB2 0SR,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5365-8760","authenticated-orcid":false,"given":"Stephen","family":"Burgess","sequence":"additional","affiliation":[{"name":"MRC Biostatistics Unit, University of Cambridge, Robinson Way , Cambridge CB2 0SR,","place":["United Kingdom"]},{"name":"British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Robinson Way , Cambridge CB2 0SR,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,11,30]]},"reference":[{"key":"2026031108164096700_kxaf043-B1","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1146\/annurev-economics-080218-025643","article-title":"Weak instruments in instrumental variables regression: theory and practice","volume":"11","author":"Andrews","year":"2019","journal-title":"Annu Rev Econ"},{"key":"2026031108164096700_kxaf043-B2","doi-asserted-by":"crossref","first-page":"979","DOI":"10.2307\/2937954","article-title":"Does compulsory school attendance affect schooling and earnings?","volume":"106","author":"Angrist","year":"1991","journal-title":"Q J Econ"},{"key":"2026031108164096700_kxaf043-B3","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1016\/j.cell.2016.10.042","article-title":"The allelic landscape of human blood cell trait variation and links to common complex disease","volume":"167","author":"Astle","year":"2016","journal-title":"Cell"},{"key":"2026031108164096700_kxaf043-B4","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1093\/ije\/dyy258","article-title":"Improving the accuracy of two-sample summary-data mendelian randomization: moving beyond the nome assumption","volume":"48","author":"Bowden","year":"2019","journal-title":"Int J Epidemiol"},{"key":"2026031108164096700_kxaf043-B5","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1086\/692712","article-title":"Beyond late with a discrete instrument","volume":"125","author":"Brinch","year":"2017","journal-title":"J Polit Econ"},{"key":"2026031108164096700_kxaf043-B6","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1159\/000531659","article-title":"Violation of the constant genetic effect assumption can result in biased estimates for non-linear mendelian randomization","volume":"88","author":"Burgess","year":"2023","journal-title":"Hum Hered"},{"key":"2026031108164096700_kxaf043-B7","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1097\/EDE.0000000000000161","article-title":"Instrumental variable analysis with a nonlinear exposure\u2013outcome relationship","volume":"25","author":"Burgess","year":"2014","journal-title":"Epidemiology"},{"key":"2026031108164096700_kxaf043-B8","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1016\/j.jeconom.2005.02.009","article-title":"Instrumental quantile regression inference for structural and treatment effect models","volume":"132","author":"Chernozhukov","year":"2006","journal-title":"J Econom"},{"key":"2026031108164096700_kxaf043-B9","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1093\/ije\/dyp334","article-title":"Illustrating bias due to conditioning on a collider","volume":"39","author":"Cole","year":"2010","journal-title":"Int J Epidemiol"},{"key":"2026031108164096700_kxaf043-B10","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1007\/BF01404567","article-title":"Smoothing noisy data with spline functions","volume":"31","author":"Craven","year":"1978","journal-title":"Numer Math"},{"key":"2026031108164096700_kxaf043-B11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/ije\/dyg070","article-title":"\u2018Mendelian randomization\u2019: can genetic epidemiology contribute to understanding environmental determinants of disease?","volume":"32","author":"Davey Smith","year":"2003","journal-title":"Int J Epidemiol"},{"key":"2026031108164096700_kxaf043-B12","first-page":"1","article-title":"Erroneous epidemiological findings on vitamins: coming full circle after two decades of mendelian randomization?","volume":"54","author":"Davey Smith","year":"2025","journal-title":"Int J Epidemiol"},{"key":"2026031108164096700_kxaf043-B13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1979.tb01052.x","article-title":"Conditional independence in statistical theory","volume":"41","author":"Dawid","year":"1979","journal-title":"J R Stat Soc Ser B Stat Methodol"},{"key":"2026031108164096700_kxaf043-B14","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1177\/0962280206077743","article-title":"Mendelian randomization as an instrumental variable approach to causal inference","volume":"16","author":"Didelez","year":"2007","journal-title":"Stat Methods Med Res"},{"key":"2026031108164096700_kxaf043-B15","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.3982\/ECTA5317","article-title":"Identification of treatment effects using control functions in models with continuous, endogenous treatment and heterogeneous effects","volume":"76","author":"Florens","year":"2008","journal-title":"Econometrica"},{"key":"2026031108164096700_kxaf043-B16","first-page":"131756","article-title":"Nonparametric instrumental variable regression through stochastic approximate gradients","volume":"37","author":"Fonseca","year":"2025","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026031108164096700_kxaf043-B17","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1111\/j.0006-341X.2002.00021.x","article-title":"Principal stratification in causal inference","volume":"58","author":"Frangakis","year":"2002","journal-title":"Biometrics"},{"key":"2026031108164096700_kxaf043-B18","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1093\/ije\/29.4.722","article-title":"An introduction to instrumental variables for epidemiologists","volume":"29","author":"Greenland","year":"2000","journal-title":"Int J Epidemiol"},{"key":"2026031108164096700_kxaf043-B19","first-page":"3448","article-title":"Control function instrumental variable estimation of nonlinear causal effect models","volume":"17","author":"Guo","year":"2016","journal-title":"J Mach Learn Res"},{"key":"2026031108164096700_kxaf043-B20","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1007\/s10654-024-01113-9","article-title":"Non-linear mendelian randomization: detection of biases using negative controls with a focus on BMI, vitamin D and LDL cholesterol","volume":"39","author":"Hamilton","year":"2024","journal-title":"Eur J Epidemiol"},{"key":"2026031108164096700_kxaf043-B21","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1007\/s10654-025-01208-x","article-title":"Non-linear mendelian randomization: evaluation of effect modification in the residual and doubly-ranked methods with simulated and empirical examples","volume":"40","author":"Hamilton","year":"2025","journal-title":"Eur J Epidemiol"},{"key":"2026031108164096700_kxaf043-B22","first-page":"1414","author":"Hartford","year":"2017"},{"key":"2026031108164096700_kxaf043-B23","volume-title":"Statistical meta-analysis with applications","author":"Hartung","year":"2011"},{"key":"2026031108164096700_kxaf043-B24","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1093\/biostatistics\/kxac051","article-title":"Delivr: a deep learning approach to iv regression for testing nonlinear causal effects in transcriptome-wide association studies","volume":"25","author":"He","year":"2024","journal-title":"Biostatistics"},{"key":"2026031108164096700_kxaf043-B25","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/0304-4076(85)90139-3","article-title":"Alternative methods for evaluating the impact of interventions: an overview","volume":"30","author":"Heckman","year":"1985","journal-title":"J Econom"},{"key":"2026031108164096700_kxaf043-B26","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1097\/01.ede.0000135174.63482.43","article-title":"A structural approach to selection bias","volume":"15","author":"Hern\u00e1n","year":"2004","journal-title":"Epidemiology"},{"key":"2026031108164096700_kxaf043-B27","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1080\/01621459.1986.10478354","article-title":"Statistics and causal inference","volume":"81","author":"Holland","year":"1986","journal-title":"J Am Stat Assoc"},{"key":"2026031108164096700_kxaf043-B28","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1146\/annurev-economics-080213-041213","article-title":"Ill-posed inverse problems in economics","volume":"6","author":"Horowitz","year":"2014","journal-title":"Annu Rev Econ"},{"key":"2026031108164096700_kxaf043-B29","first-page":"467","article-title":"Identification and estimation of local average treatment effects","volume":"62","author":"Imbens","year":"1994","journal-title":"Econ J Econ Soc"},{"key":"2026031108164096700_kxaf043-B30","doi-asserted-by":"crossref","first-page":"dyae046","DOI":"10.1093\/ije\/dyae046","article-title":"Alcohol consumption and the risk of all-cause and cause-specific mortality\u2014a linear and nonlinear mendelian randomization study","volume":"53","author":"Kassaw","year":"2024","journal-title":"Int J Epidemiol"},{"key":"2026031108164096700_kxaf043-B31","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1002\/sim.3034","article-title":"Mendelian randomization: using genes as instruments for making causal inferences in epidemiology","volume":"27","author":"Lawlor","year":"2008","journal-title":"Stat Med"},{"key":"2026031108164096700_kxaf043-B32","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1038\/s41588-018-0307-5","article-title":"Association studies of up to 1.2 million individuals yield new insights into the genetic etiology of tobacco and alcohol use","volume":"51","author":"Liu","year":"2019","journal-title":"Nat Genet"},{"key":"2026031108164096700_kxaf043-B33","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1097\/01.ede.0000215160.88317.cb","article-title":"Instrumental variables: application and limitations","volume":"17","author":"Martens","year":"2006","journal-title":"Epidemiology"},{"key":"2026031108164096700_kxaf043-B34","first-page":"125","author":"Nelson","year":"1990"},{"key":"2026031108164096700_kxaf043-B35","first-page":"967","author":"Nelson","year":"1990"},{"key":"2026031108164096700_kxaf043-B36","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1111\/1468-0262.00459","article-title":"Instrumental variable estimation of nonparametric models","volume":"71","author":"Newey","year":"2003","journal-title":"Econometrica"},{"key":"2026031108164096700_kxaf043-B37","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511803161","volume-title":"Causality","author":"Pearl","year":"2009"},{"key":"2026031108164096700_kxaf043-B38","doi-asserted-by":"crossref","DOI":"10.1007\/b98888","volume-title":"Functional data analysis","author":"Ramsay","year":"2005"},{"key":"2026031108164096700_kxaf043-B39","first-page":"2013","article-title":"Single world intervention graphs (swigs): a unification of the counterfactual and graphical approaches to causality","volume":"128","author":"Richardson","year":"2013","journal-title":"Center Stat Soc Sci Univ Washington Ser"},{"key":"2026031108164096700_kxaf043-B40","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1037\/h0037350","article-title":"Estimating causal effects of treatments in randomized and nonrandomized studies","volume":"66","author":"Rubin","year":"1974","journal-title":"J Educ Psychol"},{"key":"2026031108164096700_kxaf043-B41","first-page":"591","article-title":"Randomization analysis of experimental data: the fisher randomization test comment","volume":"75","author":"Rubin","year":"1980","journal-title":"J Am Stat Assoc"},{"key":"2026031108164096700_kxaf043-B42","first-page":"4595","article-title":"Kernel instrumental variable regression","volume":"32","author":"Singh","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026031108164096700_kxaf043-B43","doi-asserted-by":"crossref","first-page":"886","DOI":"10.1097\/EDE.0000000000000187","article-title":"Commentary: Interpretation and sensitivity analysis for the localized average causal effect curve","volume":"25","author":"Small","year":"2014","journal-title":"Epidemiology"},{"key":"2026031108164096700_kxaf043-B44","doi-asserted-by":"crossref","first-page":"e2","DOI":"10.1016\/S2213-8587(23)00287-5","article-title":"Estimating dose-response relationships for vitamin d with coronary heart disease, stroke, and all-cause mortality: observational and mendelian randomisation analyses","volume":"12","author":"Sofianopoulou","year":"2024","journal-title":"Lancet Diabetes Endocrinol"},{"key":"2026031108164096700_kxaf043-B45","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1002\/gepi.22041","article-title":"Semiparametric methods for estimation of a nonlinear exposure-outcome relationship using instrumental variables with application to mendelian randomization","volume":"41","author":"Staley","year":"2017","journal-title":"Genet Epidemiol"},{"key":"2026031108164096700_kxaf043-B46","doi-asserted-by":"crossref","first-page":"e1001779","DOI":"10.1371\/journal.pmed.1001779","article-title":"UK Biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age","volume":"12","author":"Sudlow","year":"2015","journal-title":"PLoS Med"},{"key":"2026031108164096700_kxaf043-B47","first-page":"100124","article-title":"Polynomial mendelian randomization reveals non-linear causal effects for obesity-related traits","volume":"3","author":"Sulc","year":"2022","journal-title":"HGG Adv"},{"key":"2026031108164096700_kxaf043-B48","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1146\/annurev.economics.050708.143401","article-title":"Partial identification in econometrics","volume":"2","author":"Tamer","year":"2010","journal-title":"Annu Rev Econ"},{"key":"2026031108164096700_kxaf043-B49","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.ehb.2013.12.002","article-title":"Mendelian randomization in health research: using appropriate genetic variants and avoiding biased estimates","volume":"13","author":"Taylor","year":"2014","journal-title":"Econ Hum Biol"},{"key":"2026031108164096700_kxaf043-B50","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1016\/j.jhealeco.2007.09.009","article-title":"Two-stage residual inclusion estimation: addressing endogeneity in health econometric modeling","volume":"27","author":"Terza","year":"2008","journal-title":"J Health Econ"},{"key":"2026031108164096700_kxaf043-B51","doi-asserted-by":"crossref","first-page":"e1010823","DOI":"10.1371\/journal.pgen.1010823","article-title":"Relaxing parametric assumptions for non-linear mendelian randomization using a doubly-ranked stratification method","volume":"19","author":"Tian","year":"2023","journal-title":"PLoS Genet"},{"key":"2026031108164096700_kxaf043-B52","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1186\/s12874-024-02153-1","article-title":"A data-adaptive method for investigating effect heterogeneity with high-dimensional covariates in mendelian randomization","volume":"24","author":"Tian","year":"2024","journal-title":"BMC Med Res Methodol"},{"key":"2026031108164096700_kxaf043-B53","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1111\/rssb.12388","article-title":"A simple new approach to variable selection in regression, with application to genetic fine mapping","volume":"82","author":"Wang","year":"2020","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"2026031108164096700_kxaf043-B54","doi-asserted-by":"crossref","first-page":"e2352572","DOI":"10.1001\/jamanetworkopen.2023.52572","article-title":"Dose-response associations of lipid traits with coronary artery disease and mortality","volume":"7","author":"Yang","year":"2024","journal-title":"JAMA Netw Open"}],"container-title":["Biostatistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biostatistics\/article-pdf\/26\/1\/kxaf043\/65661352\/kxaf043.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biostatistics\/article-pdf\/26\/1\/kxaf043\/65661352\/kxaf043.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T12:16:52Z","timestamp":1773231412000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biostatistics\/article\/doi\/10.1093\/biostatistics\/kxaf043\/8361816"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,31]]},"references-count":54,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,12,31]]}},"URL":"https:\/\/doi.org\/10.1093\/biostatistics\/kxaf043","relation":{},"ISSN":["1465-4644","1468-4357"],"issn-type":[{"value":"1465-4644","type":"print"},{"value":"1468-4357","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2024,12,31]]},"article-number":"kxaf043"}}