On boosting the power of Chatterjee’s rank correlation

On boosting the power of Chatterjee’s rank correlation
复制标题

关于增强 Chatterjee 排名相关性的力量

DOI:
10.1093/biomet/asac048
复制
发表时间:
2022
期刊:
影响因子:
2.7
通讯作者:
Han, F.
Han, F.
中科院分区:
数学2区
文献类型:
--
作者:
Lin, Z.;Han, F.

文献摘要

参考文献

被引文献

相似文献

基于简单的秩统计首次提出的估计依赖度量的巧妙方法很快引起了人们的注意。这种依赖性的度量具有在0和1之间的吸引人的性质,并且当且仅当对应的随机变量对是独立的,或者其中一个几乎肯定是另一个的可测量函数时为0或1。然而,最近的研究(;)不幸的是,基于Chatterjee等级相关性的独立性测试对不同的本地替代方案效率很低,并且需要变体。我们通过提出对Chatterjee秩相关的改进来回答这个问题,该改进仍然一致地估计相同的依赖度量,但可证明在测试高斯旋转替代方案时实现了近参数效率。这可以通过在构造相关系数时合并许多右近邻来实现。这样,我们就克服了查特吉等级相关的“唯一的缺点”(§7)。
The ingenious approach of to estimate a measure of dependence first proposed by based on simple rank statistics has quickly caught attention. This measure of dependence has the appealing property of being between 0 and 1, and being 0 or 1 if and only if the corresponding pair of random variables is independent or one is a measurable function of the other almost surely. However, more recent studies (; ) showed that independence tests based on Chatterjee’s rank correlation are unfortunately rate inefficient against various local alternatives and they call for variants. We answer this call by proposing an improvement to Chatterjee’s rank correlation that still consistently estimates the same dependence measure, but provably achieves near-parametric efficiency in testing against Gaussian rotation alternatives. This is possible by incorporating many right nearest neighbours in constructing the correlation coefficients. We thus overcome the ‘ only one disadvantage’ of Chatterjee’s rank correlation (, § 7).
DOI: --
发表时间: 2020
期刊:
影响因子: --
作者:
Nabarun Deb;Promit Ghosal;B. Sen
通讯作者: B. Sen
DOI: --
发表时间: 1970
期刊:
影响因子: --
作者:
T. Yanagimoto
通讯作者: T. Yanagimoto
DOI: 10.3150/22-bej1529
发表时间: 2021-08
期刊: Bernoulli
影响因子: 1.5
作者:
Hongjian Shi;M. Drton;Fang Han
通讯作者: Hongjian Shi;M. Drton;Fang Han
DOI: 10.1214/07-aop370
发表时间: 2006-11
影响因子: 2.3
作者:
S. Chatterjee
通讯作者: S. Chatterjee
研究针对邻近替代方案的独立性的新测试的功效和稳健性
DOI: 10.1214/16-ejs1107
发表时间: 2016
影响因子: 1.1
作者:
S. Dhar;A. Dassios;Wicher P. Bergsma
通讯作者: Wicher P. Bergsma