Sources of high leverage in linear regression model

TL;DR

This paper analytically investigates the sources of high leverage in linear regression by decomposing leverage into meaningful components, providing insights for data analysis and potential remedial actions.

Contribution

It introduces a decomposition approach to understand high leverage points in linear regression, aiding in better diagnostics and data cleaning.

Findings

Leverage can be decomposed into meaningful components.

Decomposition helps identify sources of high leverage.

Results facilitate remedial actions in data analysis.

Abstract

Some reasons for high leverage are analytically investigated by decomposing leverage into meaningful components. The results in this work can be used for remedial action as a next step of data analysis.