Extreme Value Modeling of Minnesota River Flood

• Activity Number: 397
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Section for Statistical Programmers and Analysts
• Author(s): Deepak Sanjel*+ and You-Gan Wang
• Companies: Minnesota State University and University of Queensland
• Keywords: Picks over threshold method ; Bayesian ; extreme values ; Generalized Extreme Value distribution ; return levels

Abstract

Accurately modeling extreme events such as flood, fire, hurricane etc. has become more and more important. Several methods of analyzing extreme values are proposed in literature however, most of them are based on the extreme value limit distributions or some related family of distributions. In this paper we review these techniques and proposed to use Bayesian method to analyze such extreme value events. These ideas are illustrated with an analysis of Minnesota river flood data. Comparisons between different models such as Block Maxima model, Picks Over Threshold (POT) model and Bayesian approach have been made.