Distributed inference for the extreme value index

Summary In this paper we investigate a divide-and-conquer algorithm for estimating the extreme value index when data are stored in multiple machines. The oracle property of such an based on methods is not guaranteed by general theory distributed inference. We propose Hill estimator and establish its asymptotic theories. consider various cases where number observations involved each machine can be either homogeneous or heterogeneous, fixed varying according to total sample size. case provide sufficient, sometimes also necessary, condition under which holds.