Abstract
Performance of small-sample cointegration rank tests is investigated within the framework of a VEC model with skewed fat-tailed error distribution. The Monte Carlo analysis is conducted for: asymptotic test, tests with degrees-of-freedom corrections, test with Bartlett correction, bootstrap test, and bootstrap test with Bartlett correction, as a surrogate of double bootstrap test. The results indicate that the smallsample cointegration rank tests are robust to skewed fat-tailed error distribution, approximated by SU Johnson distribution, with respect to size and power of these tests.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Paper version not known
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
