Copula Link-Based Additive Models for Right-Censored Event Time Data

This article proposes an approach to estimate and make inference on the parameters of copula link-based survival models. The methodology allows for the margins to be specifiedusing flexible parametric formulations for time-to-event data, the baseline survival functionsto be modeled using monotonic splines, and each parameter of the assumed joint survival dis-tribution to depend on an additive predictor incorporating several types of covariate effects. All the model’s coefficients as well as the smoothing parameters associated with the relevantcomponents in the additive predictors are estimated using a carefully structured efficient andstable penalized likelihood algorithm. Some theoretical properties are also discussed. The proposed modeling framework is evaluated in a simulation study and illustrated using a real dataset. The relevant numerical computations can be easily carried out using the freely available GJRM R package