Труды российских конференций

Heavy-tailed distributions are typical for phenomena in complex multi-component systems. They possess a number of specific features including the slower than exponential decay to zero of the tail, the violation of Cramer’s condition, a possible non-existence of some moments, and sparse observations in the tail of the distribution. Consequently the analysis of such distributions requires unique statistical methods. I introduce these statistical techniques. I provide a survey of classical results and explores the recent developments in the theory of nonparametric estimation of the heavy-tailed probability density function and its application to the classification when the objects belong to populations distributed with heavy tails, the tail index, high quantiles, the hazard rate.

Полный текст доклада в формате PDF