Year of Graduation
On Approach of Detecting Structural Breaks for GARCH Models Using Likelihood Ratio Test
The paper proposes a new method of structural breaks detection in time series in the piecewise-specified GARCH-models. The method is based on the introduced Moving Likelihood Ratio (MLR) statistics. Lower and upper 99 %- bounds were found for the likelihood ratio statistics, and the criterion of structural breaks based on these bounds has been worked out. The proposed method was compared with well-known CUSUM-method using Monte Carlo numerical experiment. Results of the performed calculations showed that the accuracy of methods is comparable, however the proposed method detects the correct number of structural breaks more often than CUSUM. The method is tested on the real data when detecting the structural breaks in the volatility of returns for “Gazprom” ordinary shares.