Skip to content
Research Article Open access CC BY 4.0

Detection of and Adjustment for Multiple Unmeasured Confounding Variables in Logistic Regression by Bayesian Structural Equation Modeling

Emil Kupek

Journal of Advances in Medical and Pharmaceutical Sciences · pp. 42–51 · Published 7 Mar 2015

10.9734/JAMPS/2015/16185

Abstract

Aim: To compare the bias magnitude between logistic regression and Bayesian structural equation modeling (SEM) in a small sample with strong unmeasured confounding from two correlated latent variables. Study Design: Statistical analysis of artificial data. Methodology: Artificial binary data with above characteristics were generated and analyzed by logistic regression and Bayesian SEM over a plausible range of model parameters deduced by comparing the parameter bounds for two extreme scenarios of no versus maximum confounding. Results: Bayesian SEM with flat priors achieved almost fourfold absolute bias reduction for the effects of observed independent variables on binary outcome in the presence of two correlated unmeasured confounders in comparison with standard logistic regression which ignored the confounding. The reduction was achieved despite a relatively small sample (N=100) and large bias and variance of the factor loadings for the latent confounding variables. However, the magnitude of residual confounding was still high.  Conclusion: Logistic regression bias due to unmeasured confounding may be considerably reduced with Bayesian SEM even in small samples with multiple confounders. The assumptions for Bayesian SEM are far less restrictive than those for the instrumental variable method aimed at correcting the effect size bias due to unmeasured confounders.  

Bias bayesian statistics observational studies confounding

References (22)

  1. 1 Marginal Structural Models and Causal Inference in Epidemiology [DOI]
  2. 2 Exploratory Structural Equation Modeling [DOI]
  3. 3 Instruments for Causal Inference [DOI]
  4. 4 An Introduction to Causal Inference [DOI]
  5. 5 Assessing the Sensitivity of Regression Results to Unmeasured Confounders in Observational Studies [DOI]
  6. 6 The Impact of Residual and Unmeasured Confounding in Epidemiologic Studies: A Simulation Study [DOI]
  7. 7 Instrumental Variables [DOI]
  8. 8 Assessment and Control for Confounding by Indication in Observational Studies [DOI]
  9. 9 Causal Effects in Mediation Modeling: An Introduction With Applications to Latent Variables [DOI]
  10. 10 Aircraft noise and cardiovascular disease near Heathrow airport in London: small area study [DOI]
  11. 11 Causal Directed Acyclic Graphs and the Direction of Unmeasured Confounding Bias [DOI]
  12. 12 Beyond logistic regression: structural equations modelling for binary variables and its application to investigating unobserved confounders [DOI]
  13. 13 Bayesian sensitivity analysis for unmeasured confounding in observational studies [DOI]
  14. 14 Bias Formulas for External Adjustment and Sensitivity Analysis of Unmeasured Confounders [DOI]
  15. 15 Alternatives to randomisation in the evaluation of public-health interventions: statistical analysis and causal inference [DOI]
  16. 16 Mortality rates at 10 years after metal-on-metal hip resurfacing compared with total hip replacement in England: retrospective cohort analysis of hospital episode statistics [DOI]
  17. 17 Mediation from Multilevel to Structural Equation Modeling [DOI]
  18. 18 Bounding Causal Effects Under Uncontrolled Confounding Using Counterfactuals [DOI]
  19. 19 Control for confounding in the presence of measurement error in hierarchical models [DOI]
  20. 20 Hierarchical priors for bias parameters in Bayesian sensitivity analysis for unmeasured confounding [DOI]
  21. 21 Modelling determinants, impact, and space–time risk of age-specific mortality in rural South Africa: integrating methods to enhance policy relevance [DOI]
  22. 22 Applied logistic regression [DOI]

Cited by 0

No indexed citations yet.

Related research

Article metrics

Real usage data collected on this platform.

59

Page views

0

PDF downloads

45

Outbound clicks

0

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.