The Comparison of Performances of Widely Used Cointegration Tests

Abstract

The aim of this study is to compare performances of commonly cointegration tests used in literature in terms of their empirical power and type I error probabilty for various sample sizes. As a result of the study, it has been found that some tests are not appropriate in testing cointegration in terms of empirical power and type I error probability. As a result of simulation study, (max) test for any values of and sample sizes have been found most appropriate test in conclusion.