Brian J. Reich
    Assistant Professor
    Department of Statistics
    North Carolina State University

Research on Extreme Value Analysis

From heat waves to hurricanes, it is often the extremes of environmental processes that are the most critical to understand probabilistically due to their impacts on society. Statistical techniques are crucial for accurately quantifying the likelihood of extreme events and monitoring changes in their frequency and intensity. Extreme events are by definition rare, therefore estimation of local climate characteristics can be improved by borrowing strength across nearby locations. While methods for univariate extreme data are well-developed, modeling spatially-referenced extreme data is an active area of research. My work on extremes focuses of developing computationally-feasible Bayesian models for complex environmental processes such as extreme precipitation, temperature, and air pollution.

Selected papers

Reich BJ, Shaby BJ, Cooley D (2013). A hierarchical model for serially-dependent extremes: A study of heat waves in the western US. JABES.

Heat waves take a major toll on human populations, with negative impacts on the economy, agriculture, and human health. As a result, there is great interest in studying the changes over time in the probability and magnitude of heat waves. In this paper we propose a hierarchical Bayesian model for serially-dependent extreme temperatures. We assume the marginal temperature distribution follows the generalized Pareto distribution (GPD) above a location-specific threshold, and capture dependence between subsequent days using a transformed max-stable process. Our model allows both the parameters in the marginal GPD and the temporal dependence function to change over time. This permits Bayesian inference on the change in likelihood of a heat wave. We apply this methodology to daily high temperatures in nine cities in the western US for 1979-2010. Our analysis reveals increases in the probability of a heat wave in several US cities.

Shaby, Reich (2013). Bayesian spatial extreme value analysis to assess the changing risk of concurrent high temperatures across large portions of European cropland. Environmetrics.

There is strong evidence that extremely high temperatures are detrimental to the yield and quality of many economically and socially critical crops. Fortunately, the most deleterious conditions for agriculture occur rarely. We wish to assess the risk of the catastrophic scenario in which large areas of croplands experience extreme heat stress during the same growing season. Applying a hierarchical Bayesian spatial extreme value model that allows the distribution of extreme temperatures to change in time both marginally and in spatial coherence, we examine whether the risk of widespread extremely high temperatures across acricultural land in Europe has increased over the last century.

Reich, Cooley, Foley, Napelenok, Shaby (2013). Extreme value analysis for evaluating ozone control strategies. AOAS.

Tropospheric ozone has been linked to respiratory and cardiovascular endpoints and adverse effects on vegetation and ecosystems. Regional photochemical models have been developed to study the impacts of emission reductions on ozone levels. The standard approach is to run the deterministic model under new emission levels and attribute the change in ozone concentration to the emission control strategy. However, running the model requires substantial computing time, and this approach does not provide a measure of uncertainty for the change in ozone levels. Recently, a reduced form model (RFM) has been proposed to approximate the complex model as a simple function of a few relevant inputs. We develop a new approach to make full use of the RFM to study the effects of various control strategies on the probability and magnitude of extreme ozone events. We fuse the model output with monitoring data to calibrate the RFM by modeling the conditional distribution of monitoring data given the RFM using a combination of flexible semiparametric quantile regression for the center of the distribution where data are abundant and a parametric extreme value distribution for the tail where data are sparse. Due to the simplicity of the RFM, we are able to embed the RFM in our Bayesian hierarchical framework to obtain a full posterior for the model input parameters, and propagate this uncertainty to the estimation of the effects of the control strategies. We use the new framework to evaluate three potential control strategies, and find that reducing mobile-source emissions has a larger impact than reducing point-source emissions or a combination of several emission sources.

Fuentes, Henry, Reich (2013). Nonparametric Spatial Models for Extremes: Application to Extreme Temperature Data. Extremes.

Estimating the probability of extreme temperature events is difficult because of limited records across time and the need to extrapolate the distributions of these events, as opposed to just the mean, to locations where observations are not available. Another related issue is the need to characterize the uncertainty in the estimated probability of extreme events at different locations. Although the tools for statistical modeling of univariate extremes are well-developed, extending these tools to model spatial extreme data is an active area of research. In this paper, in order to make inference about spatial extreme events, we introduce a new nonparametric model for extremes. We present a Dirichlet-based copula model that is a flexible alternative to parametric copula models such as the normal and t-copula. This presents the most flexible multivariate copula approach in the literature, and allows for nonstationarity in the spatial dependence of the extremes. The proposed modelling approach is fitted using a Bayesian framework that allow us to take into account different sources of uncertainty in the data and models. We apply our methods to annual maximum temperature values in the east-south-central United States.

Reich, Shaby (2012). A hierarchical max-stable spatial model for extreme precipitation. AOAS.

Extreme environmental phenomena such as major precipitation events manifestly exhibit spatial dependence. Max-stable processes are a class of asymptotically-justified models that are capable of representing spatial dependence among extreme values. While these models satisfy modeling requirements, they are limited in their utility because their corresponding joint likelihoods are unknown for more than a trivial number of spatial locations, preventing, in particular, Bayesian analyses. In this paper, we propose a new random effects model to account for spatial dependence. We show that our specification of the random effect distribution leads to a max-stable process that has the popular Gaussian extreme value process (GEVP) as a limiting case. The proposed model is used to analyze the yearly maximum precipitation from a regional climate model.