Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress 2023 EHA Congress 2023 ASCO Annual Meeting
Clinical Collections
Advances in Alzheimer’s

At a glance: The ONWARDS insulin icodec trials

A round-up of the ONWARDS phase 3 clinical trials evaluating the novel weekly insulin icodec in people with diabetes.
ADVANCED SEARCH
Log in
Top
BMC Medical Research Methodology
Published in: BMC Medical Research Methodology 1/2017

Open Access 01-12-2017 | Research article

The alarming problems of confounding equivalence using logistic regression models in the perspective of causal diagrams

Authors: Yuanyuan Yu, Hongkai Li, Xiaoru Sun, Ping Su, Tingting Wang, Yi Liu, Zhongshang Yuan, Yanxun Liu, Fuzhong Xue

Published in: BMC Medical Research Methodology | Issue 1/2017

Login to get access

Abstract

Background

Confounders can produce spurious associations between exposure and outcome in observational studies. For majority of epidemiologists, adjusting for confounders using logistic regression model is their habitual method, though it has some problems in accuracy and precision. It is, therefore, important to highlight the problems of logistic regression and search the alternative method.

Methods

Four causal diagram models were defined to summarize confounding equivalence. Both theoretical proofs and simulation studies were performed to verify whether conditioning on different confounding equivalence sets had the same bias-reducing potential and then to select the optimum adjusting strategy, in which logistic regression model and inverse probability weighting based marginal structural model (IPW-based-MSM) were compared. The “do-calculus” was used to calculate the true causal effect of exposure on outcome, then the bias and standard error were used to evaluate the performances of different strategies.

Results

Adjusting for different sets of confounding equivalence, as judged by identical Markov boundaries, produced different bias-reducing potential in the logistic regression model. For the sets satisfied G-admissibility, adjusting for the set including all the confounders reduced the equivalent bias to the one containing the parent nodes of the outcome, while the bias after adjusting for the parent nodes of exposure was not equivalent to them. In addition, all causal effect estimations through logistic regression were biased, although the estimation after adjusting for the parent nodes of exposure was nearest to the true causal effect. However, conditioning on different confounding equivalence sets had the same bias-reducing potential under IPW-based-MSM. Compared with logistic regression, the IPW-based-MSM could obtain unbiased causal effect estimation when the adjusted confounders satisfied G-admissibility and the optimal strategy was to adjust for the parent nodes of outcome, which obtained the highest precision.

Conclusions

All adjustment strategies through logistic regression were biased for causal effect estimation, while IPW-based-MSM could always obtain unbiased estimation when the adjusted set satisfied G-admissibility. Thus, IPW-based-MSM was recommended to adjust for confounders set.
Appendix
Available only for authorised users
Literature
1.
Pearl J. The do-calculus revisited. In: Proceedings of the twenty-eighth conference on uncertainty in artificial intelligence (UAI-12); 2012. p. 4–11.
2.
3.
Howards PP, Schisterman EF, Poole C, et al. “Toward a clearer definition of confounding” revisited with directed acyclic graphs. Am J Epidemiol. 2012;176(6):506–11.CrossRefPubMedPubMedCentral
4.
Greenland S, Robins JM, Pearl J. Confounding and collapsibility in causal inference. Stat Sci. 1999;14(1):29–46.CrossRef
5.
Grimes DA, Schulz KF. Bias and causal associations in observational research. Lancet. 2002;359(9302):248–52.CrossRefPubMed
6.
MacKenzie TA, Tosteson TD, Morden NE, et al. Using instrumental variables to estimate a Cox’s proportional hazards regression subject to additive confounding. Health Serv Outcomes Res Methodol. 2014;14(1–2):54–68.CrossRefPubMedPubMedCentral
7.
Liu W, Brookhart MA, Schneeweiss S, et al. Implications of M bias in epidemiologic studies: a simulation study. Am J Epidemiol. 2012;176(10):938–48.CrossRefPubMed
8.
Robinson LD, Jewell NP. Some surprising results about covariate adjustment in logistic regression models. Int Stat Rev. 1991;59(2):227–40.CrossRef
9.
Smolle C, Tuca A, Wurzer P, et al. Complications in tissue expansion: a logistic regression analysis for risk factors. Burns. 2017;
10.
Gong X, Cui J, Jiang Z, et al. Risk factors for pedicled flap necrosis in hand soft tissue reconstruction: a multivariate logistic regression analysis. ANZ J Surg. 2017. doi:10.​1111/​ans.​13977.
11.
Mood C. Logistic regression: why we cannot do what we think we can do, and what we can do about it. Eur Sociol Rev. 2010;26(1):67–82.CrossRef
12.
13.
14.
Robins JM, Hernán MA, Brumback B. Marginal structural models and causal inference in epidemiology. Epidemiology. 2000;11(5):550–60.CrossRefPubMed
15.
Pearl J, Paz A. Confounding equivalence in causal inference. J Causal Inference. 2014;2(1):75–93.
16.
Pearl J. Invited commentary: understanding bias amplification. Am J Epidemiol. 2011;174(11):1228–9.CrossRef
17.
Pearl J. Causal inference in statistics: an overview. Stat Surv. 2009;3:96–146.CrossRef
18.
Pearl J. The deductive approach to causal inference. J Causal Inference. 2014;2(2):115–29.
19.
Pearl J. Causal diagrams and the identification of causal effects. In: Causality. Cambridge: Cambridge university press; 2009.
20.
Knüppel S, Stang A. DAG program: identifying minimal sufficient adjustment sets. Epidemiology. 2010;21(1):159.CrossRefPubMed
21.
Evans D, Chaix B, Lobbedez T, et al. Combining directed acyclic graphs and the change-in-estimate procedure as a novel approach to adjustment-variable selection in epidemiology. BMC Med Res Methodol 2012; 12(1):156-156.
22.
Greenland S, Pearl J, Robins JM. Causal diagrams for epidemiologic research. Epidemiology. 1999;10(1):37–48.
23.
VanderWeele TJ. On the relative nature of over adjustment and unnecessary adjustment. Epidemiology. 2009;20(4):496–9.CrossRefPubMed
24.
Robins JM. Causal inference from complex longitudinal data. Latent variable modeling and applications to causality. 120th ed; 1997. p. 69–117.CrossRef
25.
Robins JM, Greenland S, Hu FC. Estimation of the causal effect of a time-varying exposure on the marginal mean of a repeated binary outcome. J Am Stat Assoc. 1999;94(447):687–700.CrossRef
26.
Robins JM. Marginal structural models. 1997 Proc Am Stat Assoc. 1998; 1998: 1-10.
27.
Hernán MA, Brumback B, Robins JM. Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men. Epidemiology. 2000;11(5):561.CrossRefPubMed
28.
29.
Hosman C, Hansen B, Holland P. The sensitivity of linear regression coefficient confidence limits to the omission of a confounder. Ann Appl Stat. 2010;4(2):849–70.CrossRef
30.
Li H, Yuan Z, Su P, et al. A simulation study on matched case-control designs in the perspective of causal diagrams. BMC Med Res Methodol. 2016;16(1):102.CrossRefPubMedPubMedCentral
31.
Moffitt R. Estimating marginal treatment effects in heterogeneous populations. Ann d'Econ Stat. 2008;91(91):239–61.
32.
Heckman JJ, Vytlacil E. Structural equations, treatment effects, and econometric policy evaluation. Econometrica. 2005;73(3):669–738.CrossRef
33.
Pang M, Kaufman JS, Platt RW. Studying noncollapsibility of the odds ratio with marginal structural and logistic regression models. Stat Methods Med Res. 2016;25(5):1925–37.CrossRefPubMed
Metadata
Title
The alarming problems of confounding equivalence using logistic regression models in the perspective of causal diagrams
Authors
Yuanyuan Yu
Hongkai Li
Xiaoru Sun
Ping Su
Tingting Wang
Yi Liu
Zhongshang Yuan
Yanxun Liu
Fuzhong Xue
Publication date
01-12-2017
Publisher
BioMed Central
Published in
BMC Medical Research Methodology / Issue 1/2017
Electronic ISSN: 1471-2288
DOI
https://doi.org/10.1186/s12874-017-0449-7

Other articles of this Issue 1/2017

BMC Medical Research Methodology 1/2017 Go to the issue

Research article

Multiple imputation for handling missing outcome data when estimating the relative risk

Research article

Using Mechanical Turk to recruit participants for internet intervention research: experience from recruitment for four trials targeting hazardous alcohol consumption

Research article

The impact of self-interviews on response patterns for sensitive topics: a randomized trial of electronic delivery methods for a sexual behaviour questionnaire in rural South Africa

Research article

The feasibility of matching on a propensity score for acupuncture in a prospective cohort study of patients with chronic pain

Research article

An experimental comparison of web-push vs. paper-only survey procedures for conducting an in-depth health survey of military spouses

Debate

Towards evidence-based computational statistics: lessons from clinical research on the role and design of real-data benchmark studies