A General Condition for Avoiding Effect Reversal after Marginalization

DOI10.1111/1467-9868.00424MaRDI QIDQ4670784zbMATH OpenOpenAlexFDO

Authors Nanny Wermuth, D. R. Cox

Publication date 22 April 2005

Published in Journal of the Royal Statistical Society Series B: Statistical Methodology (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1111/1467-9868.00424

zbMATH Keywords

causalitycollapsibilitygraphsrandomizationYule-Simpson paradox

Mathematics Subject Classification ID

Characterization and structure theory of statistical distributions (62E10) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Linear regression; mixed models (62J05)

Recommendations

• Some association measures and their collapsibility
• On a generalization of a result of W. G. Cochran
• Average collapsibility of distribution dependence and quantile regression coefficients
• Marginalization and collapsibility in graphical interaction models
• Conditional and marginal association for binary random variables

Cites work

• scientific article; zbMATH DE number 1134987 (Why is no real title available?)
• Observational studies.

Cited in

(20)

• Collapsibility of some association measures and survival models
• Local structure recovery of chain graphs after marginalization
• Sequences of regressions and their independences
• Triangular systems for symmetric binary variables
• Some collapsibility results for \(n\)-dimensional contingency tables
• Collapsibility of regression coefficients and its extensions
• Average collapsibility of distribution dependence and quantile regression coefficients
• Some association measures and their collapsibility
• Collapsibility for directed acyclic graphs
• Collapsibility of Distribution Dependence
• On a generalization of a result of W. G. Cochran
• Statistics for studies of human welfare
• Conditional independence collapsibility for acyclic directed mixed graph models
• Marginal log-linear parameters and their collapsibility for categorical data
• Causality: a statistical view
• On the comparison of regression coefficients across multiple logistic models with binary predictors
• Cox reduction and confidence sets of models: a theoretical elucidation
• Identifying collapsible sets in directed graphical models via inducing paths
• Path-dependent parametric decompositions in Ising models
• Causal inference in statistics: an overview

This page was built for publication: A General Condition for Avoiding Effect Reversal after Marginalization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4670784)