EcoSta 2023: Start Registration
View Submission - EcoSta2023
A0471
Title: Marginal quantile regression for longitudinal data with time-dependent covariates and its applications Authors:  I-Chen Chen - US Centers for Disease Control and Prevention (United States) [presenting]
Abstract: Modelling the within-subject correlation structure using marginal quantile regression for longitudinal data can be difficult unless a working independence structure is utilized. Although this approach guarantees consistent estimators of the regression coefficients, it may lead to less efficient regression parameter estimation when data are highly correlated. Therefore, several marginal quantile regression methods have been proposed to improve regression parameter estimation. In a longitudinal study, some of the covariates may change their values over time, and the topic of time-dependent covariates has not been explored in the literature. Therefore, an approach for marginal quantile regression in the presence of time-dependent covariates, which includes a strategy, is proposed to select a working type of time dependency. A simulation study demonstrates that the proposed method can potentially improve power relative to the independence estimating equations approach due to the reduction of mean squared error. The proposed method in a working example and its extension to exposure and biomonitoring data from occupational studies is also discussed.