Outlier Detection in Cointegration Analysis

Standard unit-root and cointegration tests are sensitive to atypical events such as outliers and structural breaks. In this article, the authors use outlier-robust estimation techniques to examine the impact of these events on cointegration analysis. Their outlier-robust cointegration test provides a new diagnostic tool for signaling when standard cointegration results might be driven by a few aberrant observations. A main feature of the authors' approach is that the proposed robust estimator can be used to compute weights for all observations, which in turn can be used to identify the approximate dates of atypical events. The authors evaluate their method using simulated data and a Monte Carlo experiment. The authors also present an empirical example showing the usefulness of the proposed analysis.