Curse of dimensionality in multivariate extremes: a graphical modelling approach
Ioannis Papastathopoulos (University of Edinburgh)
Friday 20th March, 2015 15:00-16:00 Maths 214
Natural hazards such as floods, heatwaves and windstorms can cause havoc for the people affected and typically
result in huge financial losses. There is a clear need to have good methods to estimate the likelihoods of such events.
Motivated by the structure observed in a broad range of conditioned limit limit laws of stationary k-th order Markov processes,
we develop graphical modelling methodology that allows dimension reduction and efficient high-dimensional inference
for multivariate extremes. A statistical procedure is described and efficiency gains are illustrated via simulation.