English

Maximum likelihood estimation in the non-ergodic fractional Vasicek model

Probability 2020-01-09 v1

Abstract

We investigate the fractional Vasicek model described by the stochastic differential equation dXt=(αβXt)dt+γdBtHdX_t=(\alpha -\beta X_t)\,dt+\gamma \,dB^H_t, X0=x0X_0=x_0, driven by the fractional Brownian motion BHB^H with the known Hurst parameter H(1/2,1)H\in (1/2,1). We study the maximum likelihood estimators for unknown parameters α\alpha and β\beta in the non-ergodic case (when β<0\beta <0) for arbitrary x0Rx_0\in \mathbb{R}, generalizing the result of Tanaka, Xiao and Yu (2019) for particular x0=α/βx_0=\alpha /\beta, derive their asymptotic distributions and prove their asymptotic independence.

Keywords

Cite

@article{arxiv.2001.02489,
  title  = {Maximum likelihood estimation in the non-ergodic fractional Vasicek model},
  author = {Stanislav Lohvinenko and Kostiantyn Ralchenko},
  journal= {arXiv preprint arXiv:2001.02489},
  year   = {2020}
}

Comments

Published at https://doi.org/10.15559/19-VMSTA140 in the Modern Stochastics: Theory and Applications (https://vmsta.org/) by VTeX (http://www.vtex.lt/)

R2 v1 2026-06-23T13:05:53.091Z