Title: Efficient Likelihood-Based Inference for the Generalized Pareto Distribution

Speaker: Narayanaswamy Balakrishnan (McMaster University)

Abstract: The Generalized Pareto Distribution (GPD), introduced by Pickands, is widely used to model exceedances over thresholds.  It is well known that inference for the GPD is a difficult problem since the moments do not all exist for some range of the shape parameter and that the GPD violates the classical regularity conditions in the maximum likelihood method.  In this talk, I will describe a novel framework for inference for the GPD, which works successfully for all values of the shape parameter k.  We also derive some asymptotic properties of the proposed estimators and related statistics.  Based on these results, confidence intervals and hypothesis tests will be discussed.  Monte Carlo simulation results will be presented to demonstrate the performance of the proposed estimators, confidence intervals and hypothesis tests.  Finally, two real examples will bepresented to illustrate all the inference methods discussed.

Date/Time: Tuesday January 19, 2021, 3:30 - 4:30 

Location: Virtual