Improved two-component tests in Beta-Skew-t-EGARCH models

Abstract

This work proposes a likelihood ratio test to assist in the selection of the Beta-Skew-t-EGARCH model with one or two volatility components. To improve the performance of the proposed test in small samples, the bootstrap-based likelihood ratio test and the bootstrap Bartlett correction are considered. The finite sample performance of the tests are assessed using Monte Carlo simulations. The numerical evidence favors the bootstrap-based test. The tests are applied to the DAX log-returns. The results demonstrate the practical usefulness of the proposed two-component tests.