Stable Non-Linear Generalized Bayesian Joint Models for Survival-Longitudinal Data

Joint models have received increasing attention during recent years with extensions into various directions; numerous hazard functions, different association structures, linear and non-linear longitudinal trajectories amongst others. Here, we present a partially joint model Bayesian smoothing spline component to capture where the data can assume non-Gaussian distributions. Our approach is stable regards knot set as opposed most well-known models. We implement this method using R-INLA package show that shared Gaussian random effects are part of class latent (LGMs). an illustrative example use application real skew-normal model. This paves way for efficient implementation complex components same methodology computational platform.