Toggle Main Menu Toggle Search

Open Access padlockePrints

Heteroskedasticity and Autocorrelation Robust Inference for a System of Regression Equations

Lookup NU author(s): Dr Robert AndersonORCiD



This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).


This paper extends standard single equation heteroskedasticity and autocorrelation (HAC) robust inference methods to allow consistent inference for a system of vector moving-average correlated equations also accommodating contemporaneous correlations. This is of particular relevance to the examination of inflation forecast errors, as forecasts for different groups are contemporaneously correlated, while any proposed forecasting model utilising a time-series of multi-period forward-looking expectations data will suffer from overlapping errors inducing a moving-average error structure. The proposed methodology is a generalisation of Newey & West (1987) and the SUR technique of Zellner (1962). Monte Carlo simulations confirm that the method performs well in large samples. Applications testing the rationality of male versus female inflation forecasts, and those of defined educated groups, are also included.

Publication metadata

Author(s): Anderson RDJ, Becker R, Osborn DR

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: EcoSta 2017: 1st International Conference on Econometrics and Statistics

Year of Conference: 2017

Pages: 1-53

Online publication date: 17/06/2017

Acceptance date: 01/01/2017

Date deposited: 05/09/2017

Publisher: CMStatistics