Data Transformation and Forecasting in Models with Unit Roots and
Cointegration

John C. Chao

We perform a series of Monte Carlo experiments in order to evaluate the impact of data transformation on forecasting models, and find that vector
error-corrections dominate differenced data vector autoregressions when the correct data transformation is used, but not when data are incorrectly transformed, even if the true model contains cointegrating restrictions. We argue that one reason for this is the failure of standard unit root and cointegration tests under incorrect data transformation.