Optimal estimation of the local time and the occupation time measure for an α-stable Lévy process

Abstract

A novel theoretical result on estimation of the local time and the occupation time measure of an α-stable Lévy process with α∈(1,2) is presented. The approach is based upon computing the conditional expectation of the desired quantities given high frequency data, which is an L2-optimal statistic by construction. The corresponding stable central limit theorems are proved and a statistical application is discussed. In particular, this work extends the results of [20], which investigated the case of the Brownian motion.

The authors gratefully acknowledge financial support of ERC Consolidator Grant 815703 "STAMFORD: Statistical Methods for High Dimensional Diffusions."