Canonical Regression Quantiles with application to CEO compensation and predicting company performance

TL;DR

This paper introduces a novel regression quantile method for analyzing multiple responses, applied to study CEO compensation and company performance, offering more robust and quantile-specific insights than traditional variance-based approaches.

Contribution

The paper develops an alternative regression quantile approach for multiple responses, improving robustness and quantile analysis over classical methods based on variances.

Findings

Initial results show promising insights into CEO compensation and company performance.

Method provides quantile-specific analysis, surpassing traditional variance-based methods.

Application demonstrates practical utility in empirical corporate studies.

Abstract

In using multiple regression methods for prediction, one often considers the linear combination of explanatory variables as an index. Seeking a single such index when here are multiple responses is rather more complicated. One classical approach is to use the coefficients from the leading canonical correlation. However, methods based on variances are unable to disaggregate responses by quantile effects, lack robustness, and rely on normal assumptions for inference. We develop here an alternative regression quantile approach and apply it to an empirical study of the performance of large publicly held companies and CEO compensation. The initial results are very promising.