基于经验累积量母函数Hessian的多元正态性检验
An Effective Multivariate Normality Test via Hessians of Empirical Cumulant Generating Functions
摘要:
在这篇文章中,我们提出了一类新的一致性测试$p$ -变量的正态性。这些测试是基于标准的多元正态分布的特征,即相应的累积量生成函数的Hessian是相同的$p\times p$单位矩阵和从联合分布的信息分解到依赖copula和所有边缘分布的想法。在多元正态性的原假设下,我们提出的检验统计量独立于未知的均值向量协方差阵,从而可以通过蒙特卡罗模拟得到检验的无分布临界值.我们还推导出了所提出的检验统计量的渐近零分布,并建立了对不同固定替代品的检验的一致性。最后但并非最不重要的是,一个全面和广泛的蒙特卡洛研究也表明,我们的测试是一个极好的,但计算方便的竞争对手,许多著名的现有检验统计量。
英文摘要:
In this article, we propose a new class of consistent tests for $p$-variate normality. These tests are based on the characterization of the standard multivariate normal distribution, that the Hessian of the corresponding cumulant generating function is identical to the $p\times p$ identity matrix and the idea of decomposing the information from the joint distribution into the dependence copula and all marginal distributions. Under the null hypothesis of multivariate normality, our proposed test statistic is independent of the unknown mean vector and covariance matrix so that the distribution-free critical value of the test can be obtained by Monte Carlo simulation. We also derive the asymptotic null distribution of proposed test statistic and establish the consistency of the test against different fixed alternatives. Last but not least, a comprehensive and extensive Monte Carlo study also illustrates that our test is a superb yet computationally convenient competitor to many well-known existing test statistics.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。