Improved spread-location visualization

TL;DR

This paper enhances the spread-location plot by recommending multiple transformations and visual aids like boxplots to better diagnose residuals in statistical models.

Contribution

It introduces a multipanel visualization approach with transformations and boxplots to improve residual diagnostics over traditional spread-location plots.

Findings

Multipanel display improves residual analysis.

Transformations help achieve symmetry in residuals.

Illustrative example demonstrates practical application.

Abstract

The spread-location plot has often been used as a diagnostic plot suitable for many types of fitted statistical models. The spread-location plot which plots the absolute residual or square-root absolute residual versus fitted value along with a robust loess smooth is a useful replacement for the customary practice of plotting residuals versus fitted values. In this note, we show that neither absolute residual or square-root absolute residual is always appropriate for error distributions likely to be encountered in actual applications. Hence we recommend a multipanel display showing a suitable transformation of the absolute residual versus fitted value along with a boxplot to judge the symmetry achieved by the transformation. We conclude with an illustrative example.