Bayesian parametric survival analysis with the fused lasso

Bayesian parametric survival analysis for proportional hazards regression.

This toolbox implements a Bayesian parametric proportional hazards regression model for right-censored survival data (see also Royston and Parmar 2002). The underlying baseline hazard function is modelled via integrated splines to guarantee monotonicity. The Bayesian fused lasso prior distribution is used to control smoothness of the baseline hazard function estimate and to select important covariates. To obtain samples from the posterior distribution, we use Hamiltonian Monte Carlo in conjunction with the Proximal MCMC algorithm (Zhou et al. 2024). Usage examples are included (see example?.m).