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

Journal Title: Journal of Advances in Medical and Pharmaceutical Sciences - Year 2015, Vol 3, Issue 1

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.

Authors and Affiliations

Emil Kupek

Keywords

Related Articles

Preliminary Investigation of the Subchronic Hypolipidemic Actions of Hibiscus sabdariffa in Rats

Hibiscus sabdariffa is a popular medicinal plant that is claimed to have hypotensive and hypocholesterolemic actions in animals. The present preliminary study was conducted to assess the subchronic hypolipidemic actions...

Hydroalcoholic Extract of Alstonia scholaris Arrests Invasion of Plasmodium falciparum by Effective RBC Membrane Stabilization

Aim: Traditionally medicinal plants play a key role in malaria control. Several studies have demonstrated that alkaloids have excellent antiplasmodial potential. Alstonia scholaris is rich in alkaloid content; despite th...

Comparative Assessment of the Gastrointestinal Tolerability, Anti-inflammatory and Antipyretic Effects of Diclofenac, Ibuprofen and Nimesulide in White Albino Rats

Aim: NSAIDs is among the commonly used drug in the management of disease conditions. The study carried out comparative assessment of gastric tolerability, antipyrectic and anti inflammatory effect of diclofenac, ibuprofe...

Diagnosis of Bilateral Type-A Radix Para-Molaris on Mandibular First Molars: A Case Report

Successful endodontic treatment of a molar tooth having an additional root whether it is radix para/ento molaris; begins with proper diagnosis. Hence careful examination and assessment of intra oral peri-apical radiograp...

Extended Spectrum Beta-Lactamases in Clinical Isolates of Escherichia coli and Klebsiella pneumoniae from University of Uyo Teaching Hospital, Uyo-Nigeria

Aims: This study was aimed to investigate the prevalence of ESBL-producing Escherichia coli and Klebsiella pneumoniae in clinical samples from University of Uyo Teaching Hospital (UUTH), Uyo-Nigeria, and determine their...

Download PDF file
  • EP ID EP342655
  • DOI 10.9734/JAMPS/2015/16185
  • Views 69
  • Downloads 0

How To Cite

Emil Kupek (2015). Detection of and Adjustment for Multiple Unmeasured Confounding Variables in Logistic Regression by Bayesian Structural Equation Modeling. Journal of Advances in Medical and Pharmaceutical Sciences, 3(1), 42-51. https://europub.co.uk/articles/-A-342655