{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T05:26:55Z","timestamp":1769923615458,"version":"3.49.0"},"reference-count":13,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2019,5,13]],"date-time":"2019-05-13T00:00:00Z","timestamp":1557705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9,1]]},"abstract":"<jats:title>Summary<\/jats:title><jats:p>We derive the exact formula linking the parameters of marginal and conditional logistic regression models with binary mediators when no conditional independence assumptions can be made. The formula has the appealing property of being the sum of terms that vanish whenever parameters of the conditional models vanish, thereby recovering well-known results as particular cases. It also permits the disentangling of direct and indirect effects as well as quantifying the distortion induced by the omission of relevant covariates, opening the way to sensitivity analysis. As the parameters of the conditional models are multiplied by terms that are always bounded, the derivations may also be used to construct reasonable bounds on the parameters of interest when relevant intermediate variables are unobserved. We assume that, conditionally on a set of covariates, the data-generating process can be represented by a directed acyclic graph. We also show how the results presented here lead to the extension of path analysis to a system of binary random variables.<\/jats:p>","DOI":"10.1093\/biomet\/asz019","type":"journal-article","created":{"date-parts":[[2019,3,16]],"date-time":"2019-03-16T02:42:51Z","timestamp":1552704171000},"page":"732-739","source":"Crossref","is-referenced-by-count":11,"title":["On marginal and conditional parameters in logistic regression models"],"prefix":"10.1093","volume":"106","author":[{"given":"Elena","family":"Stanghellini","sequence":"first","affiliation":[{"name":"Department of Economics, University of Perugia, Via A. Pascoli 20, Perugia 06123, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Doretti","sequence":"additional","affiliation":[{"name":"Department of Political Science, University of Perugia, Via A. Pascoli 20, Perugia 06123, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2019,5,13]]},"reference":[{"key":"2019091012190048300_B1","doi-asserted-by":"crossref","first-page":"171","DOI":"10.2307\/2983654","article-title":"The omission or addition of an independent variate in multiple linear regression","volume":"5","author":"Cochran,","year":"1938","journal-title":"Supplement to J. R. Statist. Soc."},{"key":"2019091012190048300_B2","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1093\/biomet\/asm046","article-title":"On a generalization of a result of W. G. Cochran","volume":"94","author":"Cox,","year":"2007","journal-title":"Biometrika"},{"key":"2019091012190048300_B3","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1093\/biomet\/81.2.403","article-title":"A note on the quadratic exponential binary distribution","volume":"81","author":"Cox,","year":"1994","journal-title":"Biometrika"},{"key":"2019091012190048300_B4","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1111\/1467-9868.00424","article-title":"A general condition for avoiding effect reversal after marginalization","volume":"65","author":"Cox,","year":"2003","journal-title":"J. R. Statist. Soc. B"},{"key":"2019091012190048300_B5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1979.tb01052.x","article-title":"Conditional independence in statistical theory (with discussion)","volume":"41","author":"Dawid,","year":"1979","journal-title":"J. R. Statist. Soc. B"},{"key":"2019091012190048300_B6","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198522195.001.0001","volume-title":"Graphical Models","author":"Lauritzen,","year":"1996"},{"key":"2019091012190048300_B7","doi-asserted-by":"crossref","first-page":"948","DOI":"10.2307\/2533848","article-title":"Assessing the sensitivity of regression results to unmeasured confounders in observational studies","volume":"54","author":"Lin,","year":"1998","journal-title":"Biometrics"},{"key":"2019091012190048300_B8","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1093\/biomet\/80.4.807","article-title":"A geometric approach to assess bias due to omitted covariates in generalized linear models","volume":"80","author":"Neuhaus,","year":"1993","journal-title":"Biometrika"},{"key":"2019091012190048300_B9","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1037\/a0031034","article-title":"Mediation analysis allowing for exposure\u2013mediator interactions and causal interpretation: Theoretical assumptions and implementation with SAS and SPSS macros","volume":"18","author":"Valeri,","year":"2013","journal-title":"Psychol. Methods"},{"key":"2019091012190048300_B10","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1111\/j.2517-6161.1987.tb01706.x","article-title":"Parametric collapsibility and the lack of moderating effects in contingency tables with a dichotomous response variable","volume":"49","author":"Wermuth,","year":"1987","journal-title":"J. R. Statist. Soc.B"},{"key":"2019091012190048300_B11","doi-asserted-by":"crossref","first-page":"845","DOI":"10.3150\/10-BEJ309","article-title":"Probability distributions with summary graph structure","volume":"17","author":"Wermuth,","year":"2011","journal-title":"Bernoulli"},{"key":"2019091012190048300_B12","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1111\/j.2517-6161.1978.tb01046.x","article-title":"Collapsibility of multidimensional contingency tables","volume":"40","author":"Whittemore,","year":"1978","journal-title":"J. R. Statist. Soc. B"},{"key":"2019091012190048300_B13","first-page":"1165","article-title":"Some association measures and their collapsibility","volume":"18","author":"Xie,","year":"2008","journal-title":"Statist. Sinica"}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asz019\/28602207\/asz019.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/biomet\/article-pdf\/106\/3\/732\/29133522\/asz019.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T21:06:51Z","timestamp":1721077611000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/106\/3\/732\/5488514"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,13]]},"references-count":13,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2019,5,13]]},"published-print":{"date-parts":[[2019,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asz019","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,9]]},"published":{"date-parts":[[2019,5,13]]}}}