|
Abstract:
|
Assessing mediation effect elucidate causal pathway from an exposure to an outcome, For Survival types of outcomes, Lin et al method is commonly used for assessing mediation effect. Their method defines the mediation effect following PE ratio based on two Cox models. The model misspecification was addressed by establishing conditions under which the method is valid. Recently, Gohsh jointly modeling two AFT models, and estimating mediation effect semiparametrically by a U statistics. It overcomes model misspecification, but is computational intensive and the lack of flexibility to incorporate additional covariates. We propose jointly modeling two Cox models, is able to overcomes model misspecification problem, and is flexible and computationally feasible to incorporate additional covariates. Our simulation results show clear advantages compared to Lin's. Case study analysis ACTG019 data.
|
