Parameter estimation for reflected OU processes

TL;DR

This paper develops explicit least squares estimators for reflected Ornstein-Uhlenbeck processes, demonstrating their consistency and asymptotic normality through theoretical analysis and numerical validation.

Contribution

It introduces explicit least squares estimators for reflected OU processes and proves their statistical properties under regular conditions.

Findings

Estimators are consistent and asymptotically normal.

Numerical results confirm good performance with moderate samples.

Explicit formulas facilitate practical implementation.

Abstract

In this paper, we investigate the parameter estimation problem for reflected OU processes. Both the estimates based on continuously observed processes and discretely observed processes are considered. The explicit formulas for the estimators are derived using the least squares method. Under some regular conditions, we obtain the consistency and establish the asymptotic normality for the estimators. Numerical results show that the proposed estimators perform well with moderate sample sizes.