Empirical likelihood based testing for multivariate regular variation
针对多元正则变异性这一常用假设，提出一种基于局部经验似然的检验方法，给出非标准但分布自由的临界值，模拟和实例验证了其有限样本表现。
Multivariate regular variation is a common assumption in the statistics literature and needs to be verified in real-data applications. We develop a novel hypothesis test for multivariate regular variation, employing localized empirical likelihood. We establish the weak convergence of the test statistic to a nonstandard, distribution-free limit and hence can provide universal critical values for the test. We show the very good finite-sample behavior of the procedure through simulations and apply the test to several real-data examples.