Online Program Home
My Program

Abstract Details

Activity Number: 661 - The Climate Extremes Program at SAMSI
Type: Topic Contributed
Date/Time: Thursday, August 2, 2018 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics and the Environment
Abstract #329411 Presentation
Title: A Data-Retaining Method for Tail Estimation
Author(s): Erika Cunningham*
Companies: Duke University
Keywords: Extremes; Bayesian; Semi-parametric

Modeling of extreme weather data typically involves thresholding, or retaining only the most extreme observations, in order that the tail may "speak" and not be overwhelmed by the bulk of the data. We propose a transformation-based method that smoothly transitions from a flexible, semi-parametric estimation of the bulk to a parametric estimation of the tails without thresholding. In the limit, this method has desirable theoretical tail-matching properties. We carry out theoretical and empirical investigation to explore its practical usage at pre-limit extremes (e.g. estimating the hundred-year flood instead of the billion-year flood), comparing its performance to methods that involve thresholding.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program