An Extreme Value Bayesian Lasso for the Conditional Left and Right Tails

We introduce a novel regression model for the conditional left and right tail of a possibly heavy-tailed response. The proposed model can be used to learn the effect of covariates on an extreme value setting via a Lasso-type specification based on a Lagrangian restriction. Our model can be used to track if some covariates are significant for the lower values, but not for the (right) tail—and vice versa; in addition to this, the proposed model bypasses the need for conditional threshold selection in an extreme value theory framework. We assess the finite-sample performance of the proposed methods through a simulation study that reveals that our method recovers the true conditional distribution over a variety of simulation scenarios, along with being accurate on variable selection. Rainfall data are used to showcase how the proposed method can learn to distinguish between key drivers of moderate rainfall, against those of extreme rainfall. Supplementary materials accompanying this paper appear online.

Probabilistic Forecasts of Arctic Sea Ice Thickness

In recent decades, warming temperatures have caused sharp reductions in the volume of sea ice in the Arctic Ocean. Predicting changes in Arctic sea ice thickness is vital in a changing Arctic for making decisions about shipping and resource management in the region. We propose a statistical spatio-temporal two-stage model for sea ice thickness and use it to generate probabilistic forecasts up to three months into the future. Our approach combines a contour model to predict the ice-covered region with a Gaussian random field to model ice thickness conditional on the ice-covered region. Using the most complete estimates of sea ice thickness currently available, we apply our method to forecast Arctic sea ice thickness. Point predictions and prediction intervals from our model offer comparable accuracy and improved calibration compared with existing forecasts. We show that existing forecasts produced by ensembles of deterministic dynamic models can have large errors and poor calibration. We also show that our statistical model can generate good forecasts of aggregate quantities such as overall and regional sea ice volume. Supplementary materials accompanying this paper appear on-line.