Statistics of extremes for IID data and breakthroughs in the estimation of the extreme value index: Laurens de Haan leading contributions (Q1003317)

An overview of the history and modern state of extreme value theory and statistics is given. Limit theorems for univariate and multivariate extremes are discussed. Different estimates of the extreme value index \(\gamma\) are considered, such as the classical Hill estimator and its generalizations, the moment estimator, the peaks over threshold, maximum likelihood estimators, kernel and Q-Q estimators. Second order parameters estimation and adaptive selection of the sample fraction for \(\gamma\) estimation are described. A personal tribute of Laurens de Haan is outlined.