Evaluating Natural Course Performance in Parametric G-formula: Review of Current Practice and Illustration Based on the United Autoworkers-General Motors Cohort.
Wenxin Lu, Sally Picciotto, Sadie Costello, Hilary Colbeth, Ellen Eisen
{"title":"Evaluating Natural Course Performance in Parametric G-formula: Review of Current Practice and Illustration Based on the United Autoworkers-General Motors Cohort.","authors":"Wenxin Lu, Sally Picciotto, Sadie Costello, Hilary Colbeth, Ellen Eisen","doi":"10.1093/aje/kwae410","DOIUrl":null,"url":null,"abstract":"<p><p>The parametric g-formula is a causal inference method that appropriately adjusts for time-varying confounding affected by prior exposure. Like all parametric methods, it assumes correct model specification, usually assessed by comparing the observed outcome with the simulated outcome under no intervention (natural course). However, it is unclear how to evaluate natural course performance and whether other variables should also be considered. We reviewed current practices for evaluating model misspecification in applications of parametric g-formula. To illustrate the pitfalls of current practices, we then applied the parametric g-formula to examine cardiovascular disease mortality in relation to occupational exposure in the United Autoworkers-General Motors cohort (UAW-GM), comparing 20 parametric model sets and qualitatively assessing natural course performance for all time-varying variables over follow-up. We found that current practices of evaluating model misspecification are often insufficient, increasing risk of bias and statistical cherry picking. Based on our motivational analyses of the UAW-GM cohort, good natural course performance of the outcome does not guarantee good simulations of other covariates; poor predictions of exposures and covariates may still exist. We recommend reporting natural course performance for all time-varying variables at all time-points. Objective criteria for evaluating model misspecification in parametric g-formula need to be developed.</p>","PeriodicalId":7472,"journal":{"name":"American journal of epidemiology","volume":null,"pages":null},"PeriodicalIF":5.0000,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American journal of epidemiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/aje/kwae410","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH","Score":null,"Total":0}
引用次数: 0
Abstract
The parametric g-formula is a causal inference method that appropriately adjusts for time-varying confounding affected by prior exposure. Like all parametric methods, it assumes correct model specification, usually assessed by comparing the observed outcome with the simulated outcome under no intervention (natural course). However, it is unclear how to evaluate natural course performance and whether other variables should also be considered. We reviewed current practices for evaluating model misspecification in applications of parametric g-formula. To illustrate the pitfalls of current practices, we then applied the parametric g-formula to examine cardiovascular disease mortality in relation to occupational exposure in the United Autoworkers-General Motors cohort (UAW-GM), comparing 20 parametric model sets and qualitatively assessing natural course performance for all time-varying variables over follow-up. We found that current practices of evaluating model misspecification are often insufficient, increasing risk of bias and statistical cherry picking. Based on our motivational analyses of the UAW-GM cohort, good natural course performance of the outcome does not guarantee good simulations of other covariates; poor predictions of exposures and covariates may still exist. We recommend reporting natural course performance for all time-varying variables at all time-points. Objective criteria for evaluating model misspecification in parametric g-formula need to be developed.
参数 g 公式是一种因果推断方法,可适当调整受先前暴露影响的时变混杂因素。与所有参数法一样,它假定模型规范正确,通常通过比较观察结果与无干预情况下的模拟结果(自然过程)来评估。然而,目前尚不清楚如何评估自然过程的表现以及是否还应考虑其他变量。我们回顾了在应用参数 g 公式时评估模型失当的现行做法。为了说明当前做法的缺陷,我们随后应用参数 g 公式研究了联合汽车工人-通用汽车公司队列(UAW-GM)中与职业暴露相关的心血管疾病死亡率,比较了 20 个参数模型集,并对随访期间所有时变变量的自然过程表现进行了定性评估。我们发现,目前评估模型不规范的做法往往不够充分,增加了偏差和统计挑剔的风险。根据我们对 UAW-GM 队列的动机分析,结果的良好自然过程表现并不能保证对其他协变量的良好模拟;对暴露和协变量的不良预测可能仍然存在。我们建议报告所有时间点上所有时变变量的自然过程表现。需要制定客观的标准来评估参数 g 公式中模型的不规范性。
期刊介绍:
The American Journal of Epidemiology is the oldest and one of the premier epidemiologic journals devoted to the publication of empirical research findings, opinion pieces, and methodological developments in the field of epidemiologic research.
It is a peer-reviewed journal aimed at both fellow epidemiologists and those who use epidemiologic data, including public health workers and clinicians.