EVT – A QUICK (…AND POSSIBLY TIMELY) LOOK AT EXTREME VALUE THEORY…!


‘…In Cauda Venenum…’


This story starts, as do many of my inspirations, with a seeming throwaway phrase by a fellow professional during a session I moderated at Commodity Trading Week back in June. It was Extreme Value Theory! Now, I am no statistician, my brief is Technical Analysis which whilst using some statistics, is more an art than a science. However, I wanted to know fmore, and the more I found out, the more I wanted to write something about it…and share it with you. So here goes…


As many of you might know, I have always seen issues with using Value at Risk (VaR) as the ‘be all and end all’ tool in Risk Management. The main reason is that it does not adequately take into account the jumps in illiquid exposure in forward days/months. I guess I was not the only one, as during the last few years, when attending the annual Commodity Trading Week, I noticed a lot of Risk Departments move away from VaR and towards various forms of stress testing on their positions. This was not the only criticism of VaR that I saw. Younes Besalah at the Bank of Canada wrote in his working paper ‘Steps in Applying Extreme Value Theory to Finance:


EXTREME VALUE THEORY (EVT) IS A USEFUL SUPPLEMENTARY RISK MEASURE BECAUSE IT PROVIDES MORE APPROPRIATE DISTRIBUTIONS TO FIT EXTREME EVENTS.


A Review’ back as far as November 2000 that, ‘The VaR approach has been the subject of several criticisms. The most significant is that the majority of the parametric methods use a normal distribution approximation. Using this approximation, the risk of the high quantiles is underestimated, especially for the fat-tailed series, which are common in financial data’. He continued with ‘Investors and risk managers have become more concerned with events occurring under extreme market conditions…Extreme Value Theory (EVT) is a useful supplementary risk measure because it provides more appropriate distributions to fit extreme events. Unlike VaR methods, no assumptions are made about the nature of the original distribution of all the observations.’. So…you may still use your favourite VaR tools, but it is very much worth your while, to include some EVT tools as well!


The next questions are…where does EVT come from and what does it mean? Well this venue is way too small to cover it all. However, from what I’ve been able to piece together, EVT was pioneered by


22 | ADMISI - The Ghost In The Machine | Q3 Edition 2021


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30