University of Edinburgh
School of Mathematics and BioSS
Date: Friday 23 September, 15:10pm
Location: JCMB 5327
Speaker: Dr Spencer Wheatley, ETH Zürich, Chair of Entepreneurial Risks
Title: Detecting outliers in heavy tailed samples & two case studies in extreme risk
Abstract: Methodology for detecting outliers in univariate exponential
samples will be discussed, as developed in [1].This also has relevance
for detecting outliers in heavy-tailed (Pareto) samples, which is
interesting when studying extreme risks, and so-called "Dragon-Kings".
Examples of this application will be discussed. On another topic,
recent frequency-severity analyses of the extreme risk present in
nuclear power, as well as cyber-security will be presented, as developed
in [2,3].
[1] Wheatley, S. and Sornette, D., Multiple Outlier Detection in Samples with Exponential and Pareto Tails:
Redeeming the Inward Approach and Detecting Dragon Kings.
(<http://arxiv.org/abs/1507.08689> & <http://ssrn.com/abstract=2645709>)
[2] Wheatley, S., Maillart, T. and Sornette, D., (2016).
The Extreme Risk of Personal Data Breaches & The Erosion of Privacy.
Eur. Phys. J. B 89 (7), 1-12
[3] Wheatley, S., Sovacool, B. and Sornette, D., (2016).
Of Disasters and Dragon Kings: A Statistical Analysis of Nuclear Power
Incidents & Accidents.
Risk Analysis doi:10.1111/risa.12587, pp. 1-17
--
There will be tea and coffee after the seminar in the Mathematics Common
Room (5212).
This seminar is a part of Maxwell Institute seminar series.
--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|