The GARCH and DCC-GARCH models are used to study the volatility aggregation and dynamic relevance of China’s three kinds of nonferrous metals （copper, aluminum and zinc） pricesincorporating structural changes. The ...The GARCH and DCC-GARCH models are used to study the volatility aggregation and dynamic relevance of China’s three kinds of nonferrous metals （copper, aluminum and zinc） pricesincorporating structural changes. The results show that copper, aluminum and zinc returns have many structure breaks points, and nonferrous metals have the greatvolatilityrisk during financial crisis. From the resultsof GARCH with and without structural changes,it isfoundthat the volatility clustering of single nonferrous metal is overvalued when ignoring the structural mutation, and the return of aluminum isthe most overvalued, indicating that aluminum market is more susceptible to external shock.Furthermore,it is also foundthatdynamic volatility correlation exists in the three prices of nonferrous metals, and the structural changes have no significant effect on the volatility correlation of thethree nonferrous metals.展开更多
In this paper, the authors analyze the adequacy of GARCH-type models to analyze oil price behavior by applying two types of non-parametric tests, the Hinich portmanteau test for non-linear dependence and a frequency-d...In this paper, the authors analyze the adequacy of GARCH-type models to analyze oil price behavior by applying two types of non-parametric tests, the Hinich portmanteau test for non-linear dependence and a frequency-dominant test of time reversibility, the reverse test based on the bispectrum, to explore the high-order spectrum properties of the Mexican oil price series. The results suggest strong evidence of a non-linear structure and time irreversibility. Therefore, it does not comply with the i.i.d （independent and identically distributed） property. The non-linear dependence, however, is not consistent throughout the sample period, as indicated by a windowed test, suggesting episodic nonlinear dependence. The results imply that GARCH models cannot capture the series structure.展开更多
基金Project(71072079)supported by the National Natural Science Foundation of China
文摘The GARCH and DCC-GARCH models are used to study the volatility aggregation and dynamic relevance of China’s three kinds of nonferrous metals （copper, aluminum and zinc） pricesincorporating structural changes. The results show that copper, aluminum and zinc returns have many structure breaks points, and nonferrous metals have the greatvolatilityrisk during financial crisis. From the resultsof GARCH with and without structural changes,it isfoundthat the volatility clustering of single nonferrous metal is overvalued when ignoring the structural mutation, and the return of aluminum isthe most overvalued, indicating that aluminum market is more susceptible to external shock.Furthermore,it is also foundthatdynamic volatility correlation exists in the three prices of nonferrous metals, and the structural changes have no significant effect on the volatility correlation of thethree nonferrous metals.
文摘In this paper, the authors analyze the adequacy of GARCH-type models to analyze oil price behavior by applying two types of non-parametric tests, the Hinich portmanteau test for non-linear dependence and a frequency-dominant test of time reversibility, the reverse test based on the bispectrum, to explore the high-order spectrum properties of the Mexican oil price series. The results suggest strong evidence of a non-linear structure and time irreversibility. Therefore, it does not comply with the i.i.d （independent and identically distributed） property. The non-linear dependence, however, is not consistent throughout the sample period, as indicated by a windowed test, suggesting episodic nonlinear dependence. The results imply that GARCH models cannot capture the series structure.
