Abstract

Regression analysis is a statistical technique to model data. But the presence of outliers and influential points affects data modelling and its interpretation. Robust regression analysis is an alternative choice to this. Here we make an attempt to study six different robust estimators and their performance on multiple linear regression data. Using Monte Carlo simulation, data is generated and modelled. R software is used for simulation and study. If the fundamental assumptions are true, robust approaches operate as effectively as the OLS estimator. When outliers and leverage points are present, OLS estimators completely fail to work efficiently. Thus, robust estimators are better than OLS estimator. Among the robust estimators, the MM estimator is the best method to rely on and outperform in all situations.

Author: Lakshmi R. and Sajesh T. A.

Received on: January, 2022

Accepted on: March, 2023