Tests for the null hypothesis of cointegration: a Monte Carlo comparison

Abstract

The aim of this paper is to compare the relative performance of several tests for the null hypothesis of cointegration, in terms of size and power in finite samples. This is carried out resorting to Monte Carlo simulations, considering a range of plausible data-generating processes. As of this writing, there is no study providing guidance on the use of this type of procedures in empirical situations, with the exception of the limited studies of McCabe et al. (1997) and Haug (1996). We also analyse the impact on size and power of choosing different procedures to estimate the long-run variance of the errors. we found that the parametrically adjusted test of McCabe et al. (1997) is the most well-balanced test in terms of power and size distrortions.