A note on Farebrother’s estimator: a comparative study

Abstract

In this article, we begin by providing a theoretical comparison between Farebrother’s estimator and the ridge estimator, in terms of the MSE matrix criterion, under three distinct restrictions when $r$ is random. Additionally, we propose an estimate of parameter $k$ for Farebrother’s estimator. Subsequently, we present a Monte Carlo simulation experiment to compare Farebrother’s estimator with OLS, RLS, and ridge estimators.

Keywords:

• Mean square error
• Multicollinearity
• Ordinary least squares
• Restricted least squares
• Ridge regression

Subject classification codes:

• 62J05
• 62J07
• 62P20

Disclosure statement

The authors report there are no competing interests to declare.