Modelling Dependence in log-normal asset returns using the Gaussian copula

Loading Map....

Dr. Zdravko Botev

University of New South Wales

The distribution of sums of dependent log-normal variables has applications in, for example, the valuation of an asset portfolio driven by the Black-Scholes model, and the performance analysis of communication systems. In this talk, we will discuss some of the interesting computational challenges that arise when a Gaussian copula is used to model the dependence, and what implications this has for modelling extreme events. We give some of the reasons why the Gaussian copula model has been blamed for financial mismanagement and how it may be reinstated in some limited number of applications. Technicalities will be kept to a minimum.

Date: Wednesday, 31 May 2017

Time:
6:00pm – 6:30pm: Refreshments
6:30pm – 7:30pm: Lecture
7:45pm onwards: Dinner (at a nearby restaurant)

Biography of Zdravko Botev

Zdravko is a DECRA fellow at UNSW. His research interests include: adaptive Monte Carlo methods for rare-event probability estimation, network reliability modeling, and kernel density estimation. He is the author of one of the most widely used Matlab software scripts for nonparametric density estimation and has written jointly with D. P. Kroese and T. Taimre the Handbook of Monte Carlo Methods, published by John Wiley & Sons in 2011.

When: 31/05/2017
Time: 6:00 pm - 7:30 pm
Cost: Free
Location: UTS Maths Grid Room CB04.05.430,
Room 430, Level 5, Building 4, University of Technology,
Sydney,
NSW
Follow

Get the latest posts delivered to your mailbox:

Show Buttons
Hide Buttons