Structural Break Detection in Autoregressional Conditional Heteroskedasticity Model: Case of Student’s Distribution

Two methods of structural break detection in a piecewise generalized model of autoregressive conditional heteroscedasticity are considered. The first method is based on Kolmogorov–Smirnov statistics and is called the KS method. The second one is based on the cumulative sums and is called the KL method. In this paper, the KS and KL methods are compared under the assumption of Student’s conditional distribution of random errors. The results of our Monte Carlo experiments are as follows: the KL method is inferior to the KS method both in terms of the average probability of errors of the first type and in terms of the average power of detecting a structural break.