An Introduction to G Methods

Naimi, Ashley I.; Cole, Stephen R.; Kennedy, Edward H.

doi:10.1093/ije/dyw323

Cited by 191 publications

(222 citation statements)

References 15 publications

Supporting

Mentioning

222

Contrasting

Order By: Relevance

“…Using this information, a minimally sufficient set of adjustment variables can be determined to control for all known confounding. Utilize longitudinal study designs and modern epidemiologic and analytic methods to examine the causal effect of opioids on OUDs in observational data. For example, methods like marginal structural models using inverse probability of treatment weighting and g‐formula could allow for effect estimation of time‐varying opioid exposure‐outcome relationships, while controlling for time‐varying confounding (internal validity). Additionally, instrumental variable approaches under a natural experiment could allow for improved estimation of the effect of opioid exposure on OUDs. Consider examining effect measure modification or even biologic interaction due to cancer rather than excluding cancer pain patients or pooling them with noncancer pain patients.…”

Section: Discussion and Recommendationsmentioning

confidence: 99%

Methodologic limitations of prescription opioid safety research and recommendations for improving the evidence base

Ranapurwala

Naumann

Austin

et al. 2018

Pharmacoepidemiology and Drug

View full text Add to dashboard Cite

show abstract

Section: Discussion and Recommendationsmentioning

confidence: 99%

Methodologic limitations of prescription opioid safety research and recommendations for improving the evidence base

Ranapurwala

Naumann

Austin

et al. 2018

Pharmacoepidemiology and Drug

View full text Add to dashboard Cite

show abstract

“…The variable H acts as a time-varying confounder on the causal pathway: it both contains a portion of the effect of past exposure (A 1 → H → Y) and acts as a confounder of the future exposure-response relationship (A 2 ← H → Y). Estimation of unbiased causal effects of exposure from data structures including these pathways requires the use of a class of modern statistical estimation approaches known collectively as g-methods [25–28]. …”

Section: Target Parametersmentioning

confidence: 99%

The Healthy Worker Survivor Effect: Target Parameters and Target Populations

Brown

Picciotto

Costello

et al. 2017

Curr Envir Health Rpt

View full text Add to dashboard Cite

Purpose of Review We offer an in-depth discussion of the time-varying confounding and selection bias mechanisms that give rise to the healthy worker survivor effect (HWSE). Recent Findings In this update of an earlier review, we distinguish between the mechanisms collectively known as the HWSE and the statistical bias that can result. This discussion highlights the importance of identifying both the target parameter and the target population for any research question in occupational epidemiology. Target parameters can correspond to hypothetical workplace interventions; we explore whether these target parameters’ true values reflect the etiologic effect of an exposure on an outcome or the potential impact of enforcing an exposure limit in a more realistic setting. If a cohort includes workers hired before the start of follow-up, HWSE mechanisms can limit the transportability of the estimates to other target populations. Summary We summarize recent publications that applied g-methods to control for the HWSE, focusing on their target parameters, target populations, and hypothetical interventions.

show abstract

“…Interested readers looking for the next step in understanding G methods are encouraged to read a recent tutorial written for epidemiologists. 25 We thank Stephen Cole for helpful comments on earlier drafts of this paper.…”

Section: Resultsmentioning

confidence: 99%

Handling time varying confounding in observational research

Mansournia

Etminan

Danaei

et al. 2017

BMJ

237

206

View full text Add to dashboard Cite

Many exposures of epidemiological interest are time varying, and the values of potential confounders may change over time leading to time varying confounding. The aim of many longitudinal studies is to estimate the causal effect of a time varying exposure on an outcome that requires adjusting for time varying confounding. Time varying confounding affected by previous exposure often occurs in practice, but it is usually adjusted for by using conventional analytical methods such as time dependent Cox regression, random effects models, or generalised estimating equations, which are known to provide biased effect estimates in this setting. This article explains time varying confounding affected by previous exposure and outlines three causal methods proposed to appropriately adjust for this potential bias: inverseprobability-of-treatment weighting, the parametric G formula, and G estimation. Many longitudinal studies aim to estimate the overall causal effect of a time varying exposure on the outcome, which requires adjustment for time varying confounding. However, in certain clinical scenarios one or more time varying confounders are affected by past exposure. In our clinical example, serum testosterone level is the time varying confounder because doctors are likely to use the value of testosterone to titrate treatment. The level of testosterone after baseline is, however, affected by baseline testosterone treatment. This pattern, for lack of a shorter term, is referred to as "time varying confounding affected by past exposure."The problem: controlling for time varying confounding affected by past exposure Several methods can control confounding in observational studies at the design and analysis stages, including restriction, stratification, regression modelling, matching, and propensity scoring. Summary poinTS• Many exposures of epidemiological interest are time varying, and time varying confounding affected by past exposure often occurs in practice• Time varying confounding affected by past exposure is often adjusted for by using conventional analytical methods such as time dependent Cox regression, random effects models, or generalised estimating equations in clinical research, which are known to provide biased effect estimates in this setting• Three causal methods have been proposed to appropriately adjust for time varying confounders that are affected by past exposure: inverse-probability-oftreatment weighting, parametric G formula, and G estimation

show abstract

An Introduction to G Methods

Cited by 191 publications

References 15 publications

Methodologic limitations of prescription opioid safety research and recommendations for improving the evidence base

Methodologic limitations of prescription opioid safety research and recommendations for improving the evidence base

The Healthy Worker Survivor Effect: Target Parameters and Target Populations

Handling time varying confounding in observational research

Contact Info

Product

Resources

About