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
The conditional kernel correlation is proposed to measure the relationship between two random variables under covariates for multivariate data.Relying on the framework of reproducing kernel Hilbert spaces,we give the ...The conditional kernel correlation is proposed to measure the relationship between two random variables under covariates for multivariate data.Relying on the framework of reproducing kernel Hilbert spaces,we give the definitions of the conditional kernel covariance and conditional kernel correlation.We also provide their respective sample estimators and give the asymptotic properties,which help us construct a conditional independence test.According to the numerical results,the proposed test is more effective compared to the existing one under the considered scenarios.A real data is further analyzed to illustrate the efficacy of the proposed method.展开更多
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.
基金partially supported by Knowledge Innovation Program of Hubei Province(No.2019CFB810)partially supported by NSFC(No.12325110)the CAS Project for Young Scientists in Basic Research(No.YSBR-034)。
文摘The conditional kernel correlation is proposed to measure the relationship between two random variables under covariates for multivariate data.Relying on the framework of reproducing kernel Hilbert spaces,we give the definitions of the conditional kernel covariance and conditional kernel correlation.We also provide their respective sample estimators and give the asymptotic properties,which help us construct a conditional independence test.According to the numerical results,the proposed test is more effective compared to the existing one under the considered scenarios.A real data is further analyzed to illustrate the efficacy of the proposed method.
