Heavy tail estimation with wavelets and internet traffic

Rudolf Riedi, Dept of Statistics, Rice University

Heavy tailed distributions become of increasing importance in
various applications as the arsenal of analytical and numerical
tools grows. Examples of interest include the Stable and more
generally the Pareto distributions for which moments beyond a
critical order diverge. Applications include network traffic
modelling, quantitative finance and turbulence, to name but a few.
This talk provides a non-parametric wavelet-based estimator of the
critical order of moments and compares it to standard estimators
of the tail parameter of stable and Pareto distributions. If time
permits, applications to multifractal model identification and to
networking are discussed.