A0642
Title: Bayesian ridge regression for survival data based on a vine copula based prior
Authors: Takeshi Emura - The Institute of Statistical Mathematics (Japan) [presenting]
Hirofumi Michimae - Kitasato University (Japan)
Abstract: Ridge regression with the Cox model is regarded as a Bayesian estimator with a multivariate normal prior. The vine copula-based priors are proposed for Bayesian Cox ridge estimators under the proportional hazards model. The vine copula allows the tail dependence that is not possible by multivariate normal priors. The semiparametric Cox models are built on the posterior density under two likelihoods: Cox's partial likelihood and the full likelihood under the gamma process prior. It is also shown via simulations and a data example that the Archimedean vine copula priors (the Clayton and Gumbel copula) are superior to the multivariate normal prior and the Gaussian copula prior.
