A comparison study of extreme precipitation from six different regional climate models via spatial hierarchical modeling (Q549647)

Extreme precipitation is investigated based on data simulated by six regional climate models (RCM) from the North American Regional Climate Change Assessment Program (NARCCAP). A hierarchical Bayesian model is used with a Generalized Extreme Value (GEV) distribution of the local data in which the spatial distribution of parameters is described by a regression model with multivariate spatial random effects. The IAR (improper spatial conditional autoregressive) model is used as the prior distribution of this random effect. The model is implemented using a Markov chain Monte Carlo simulation with a Gibbs sampler.