Robust Inference for Seemingly Unrelated Regression Models

TL;DR

This paper develops robust statistical methods for seemingly unrelated regression models, introducing MM-estimators and a bootstrap procedure to improve inference accuracy under data contamination and correlation among errors.

Contribution

It introduces MM-estimators with high breakdown point and efficiency, along with a robust bootstrap method for inference in seemingly unrelated regressions, and a test for disturbance correlation.

Findings

Robust estimators outperform traditional methods in contaminated data scenarios.

The bootstrap procedure provides reliable confidence intervals and hypothesis tests.

Simulation studies demonstrate improved inference accuracy.

Abstract

Seemingly unrelated regression models generalize linear regression models by considering multiple regression equations that are linked by contemporaneously correlated disturbances. Robust inference for seemingly unrelated regression models is considered. MM-estimators are introduced to obtain estimators that have both a high breakdown point and a high normal efficiency. A fast and robust bootstrap procedure is developed to obtain robust inference for these estimators. Confidence intervals for the model parameters as well as hypothesis tests for linear restrictions of the regression coefficients in seemingly unrelated regression models are constructed. Moreover, in order to evaluate the need for a seemingly unrelated regression model, a robust procedure is proposed to test for the presence of correlation among the disturbances. The performance of the fast and robust bootstrap inference is evaluated empirically in simulation studies and illustrated on real data.