On the power of panel cointegration tests: A Monte Carlo comparison. Economics Letters, 80(1):105-111.

This paper enlarges on Karlsoon and Löthgreen’s (2000) results on panel unit root tests to panel cointegration tests. We show that for homogeneous panel, Kao’s (1999) tests have higher (lower) power than Pedroni’s (1999) tests when a small-T (high-T) number of observations are included in the panel and both tests show better performance than Larsson et al. (2001) test. In addition, depending on the T-dimension of the panel, cointegration tests can have high power when a small or high fraction of the relationships are cointegrated. This result suggests that when rejecting the null hypothesis of no cointegration for the whole panel not all the relationships can be really cointegrated.