TY - JOUR

T1 - Understanding marginal structural models for time-varying exposures

T2 - Pitfalls and tips

AU - Shinozaki, Tomohiro

AU - Suzuki, Etsuji

N1 - Funding Information:
Funding: This work was supported by Japan Society for the Promotion of Science (KAKENHI Grant Numbers JP20K11716 and JP20K10471). Conflicts of interest: None declared.
Publisher Copyright:
© 2020 Tomohiro Shinozaki et al.

PY - 2020

Y1 - 2020

N2 - Epidemiologists are increasingly encountering complex longitudinal data, in which exposures and their confounders vary during follow-up. When a prior exposure affects the confounders of the subsequent exposures, estimating the effects of the time-varying exposures requires special statistical techniques, possibly with structural (ie, counterfactual) models for targeted effects, even if all confounders are accurately measured. Among the methods used to estimate such effects, which can be cast as a marginal structural model in a straightforward way, one popular approach is inverse probability weighting. Despite the seemingly intuitive theory and easy-to-implement software, misunderstandings (or “pitfalls”) remain. For example, one may mistakenly equate marginal structural models with inverse probability weighting, failing to distinguish a marginal structural model encoding the causal parameters of interest from a nuisance model for exposure probability, and thereby failing to separate the problems of variable selection and model specification for these distinct models. Assuming the causal parameters of interest are identified given the study design and measurements, we provide a step-by-step illustration of generalized computation of standardization (called the g-formula) and inverse probability weighting, as well as the specification of marginal structural models, particularly for time-varying exposures. We use a novel hypothetical example, which allows us access to typically hidden potential outcomes. This illustration provides steppingstones (or “tips”) to understand more concretely the estimation of the effects of complex time-varying exposures.

AB - Epidemiologists are increasingly encountering complex longitudinal data, in which exposures and their confounders vary during follow-up. When a prior exposure affects the confounders of the subsequent exposures, estimating the effects of the time-varying exposures requires special statistical techniques, possibly with structural (ie, counterfactual) models for targeted effects, even if all confounders are accurately measured. Among the methods used to estimate such effects, which can be cast as a marginal structural model in a straightforward way, one popular approach is inverse probability weighting. Despite the seemingly intuitive theory and easy-to-implement software, misunderstandings (or “pitfalls”) remain. For example, one may mistakenly equate marginal structural models with inverse probability weighting, failing to distinguish a marginal structural model encoding the causal parameters of interest from a nuisance model for exposure probability, and thereby failing to separate the problems of variable selection and model specification for these distinct models. Assuming the causal parameters of interest are identified given the study design and measurements, we provide a step-by-step illustration of generalized computation of standardization (called the g-formula) and inverse probability weighting, as well as the specification of marginal structural models, particularly for time-varying exposures. We use a novel hypothetical example, which allows us access to typically hidden potential outcomes. This illustration provides steppingstones (or “tips”) to understand more concretely the estimation of the effects of complex time-varying exposures.

KW - Causal inference

KW - G-formula

KW - Inverse probability weighting

KW - Marginal structural model

KW - Time-varying exposure

UR - http://www.scopus.com/inward/record.url?scp=85090508023&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85090508023&partnerID=8YFLogxK

U2 - 10.2188/jea.JE20200226

DO - 10.2188/jea.JE20200226

M3 - Article

C2 - 32684529

AN - SCOPUS:85090508023

VL - 30

SP - 377

EP - 389

JO - Journal of Epidemiology

JF - Journal of Epidemiology

SN - 0917-5040

IS - 9

ER -