LAUSR

We propose a novel mixture Generalized Pareto (MIXGP) model to calibrate extreme precipitation forecasts. This model is able to describe the marginal distribution of observed precipitation and capture the dependence between climate forecasts and the observed precipitation under suitable conditions. In addition, the full range distribution of precipitation conditional on grid forecast ensembles can also be estimated. Unlike the classical Generalized Pareto distribution that can only model points over a hard threshold, our model takes the threshold as a latent parameter. Tail behavior of both univariate and bivariate models are studied. The utility of our model is evaluated in Monte Carlo simulation study and is applied to precipitation data for the US where it outperforms competing methods.