A comparison of full model specification and backward elimination of potential confounders when estimating marginal and conditional causal effects on binary outcomes from observational data

DOI10.1002/bimj.202100237zbMATH Open1547.62347MaRDI QIDQ6625330

Rolf H. H. Groenwold, Georg Heinze, Maarten van Smeden, Kim Luijken, Susanne Strohmaier

Publication date: 28 October 2024

Published in: Biometrical Journal (Search for Journal in Brave)

zbMATH Keywords

causal inferencebackward eliminationconfounder selection

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10)

Cites Work

• Unnamed Item
• Valid post-selection inference
• Regression modeling strategies. With applications to linear models, logistic regression, and survival analysis
• To explain or to predict?
• A New Criterion for Confounder Selection
• Confounder selection via penalized credible regions
• Variable selection – A review and recommendations for the practicing statistician
• Bias reduction of maximum likelihood estimates
• Covariate selection strategies for causal inference: Classification and comparison
• On model selection and model misspecification in causal inference
• MODEL SELECTION AND INFERENCE: FACTS AND FICTION
• Formulating causal questions and principled statistical answers
• Using simulation studies to evaluate statistical methods
• Selection of variables for multivariable models: opportunities and limitations in quantifying model stability by resampling

This page was built for publication: A comparison of full model specification and backward elimination of potential confounders when estimating marginal and conditional causal effects on binary outcomes from observational data