A Simple Bivariate Example of Fast Convergence Rates for Maximum Likelihood Estimates
Statistics Theory
2026-05-04 v1 Statistics Theory
Abstract
We present a one-parameter family of bivariate absolutely continuous distributions based on location-scale family of variance Gaussian mixtures, with continuous densities with the same support (effective domain). The maximum likelihood estimation of the location parameter converges to the true value faster than the classic square root rate. In fact, we can obtain any convergence rate given by a regularly varying function with index greater than 0.5, and some convergence rates given by regularly varying functions with index 0.5 but faster than the classic square root rate.
Cite
@article{arxiv.2605.00198,
title = {A Simple Bivariate Example of Fast Convergence Rates for Maximum Likelihood Estimates},
author = {Andrey Sarantsev},
journal= {arXiv preprint arXiv:2605.00198},
year = {2026}
}
Comments
8 pages. Keywords: Stable subordinator, maximum likelihood estimation, Fisher information