Large deviations of regression parameter estimator in continuous-time models with sub-Gaussian noise

TL;DR

This paper derives exponential bounds for the probability of large deviations of the least squares estimator in continuous-time regression models with sub-Gaussian noise, providing insights into estimator reliability.

Contribution

It introduces new upper exponential bounds for large deviations of the estimator in models with sub-Gaussian noise, advancing theoretical understanding.

Findings

Established exponential bounds for large deviations

Analyzed estimator behavior under sub-Gaussian noise

Enhanced theoretical framework for continuous-time models

Abstract

A continuous-time regression model with a jointly strictly sub-Gaussian random noise is considered in the paper. Upper exponential bounds for probabilities of large deviations of the least squares estimator for the regression parameter are obtained.