Generalized R-squared for detecting dependence.

Generalized R-squared for detecting dependence.
复制标题

DOI:
10.1093/biomet/asw071
复制
发表时间:
2017-03
期刊:
影响因子:
2.7
通讯作者:
Liu JS
Liu JS
中科院分区:
数学2区
文献类型:
--
作者:
Wang X;Jiang B;Liu JS

文献摘要

参考文献

被引文献

相似文献

检测两个随机变量之间的相关性是一个基本问题。虽然Pearson相关系数对于捕获线性相关性是有效的,但是对于检测非线性和/或异方差模式可能完全无能为力。我们引入了一个新的措施,G平方,以测试是否两个单变量随机变量是独立的,并衡量他们的关系的强度。对于具有恒定误差方差的线性关系,G平方统计量几乎与皮尔逊相关系数的平方R平方相同,并且具有变量之间分段R平方的直观含义。它在处理非线性和异方差误差时特别有效。我们提出了两个估计的G平方,并显示其一致性。仿真结果表明,G平方估计量是最强大的测试统计相比,一些国家的最先进的方法。
Detecting dependence between two random variables is a fundamental problem. Although the Pearson correlation coefficient is effective for capturing linear dependence, it can be entirely powerless for detecting nonlinear and/or heteroscedastic patterns. We introduce a new measure, G-squared, to test whether two univariate random variables are independent and to measure the strength of their relationship. The G-squared statistic is almost identical to the square of the Pearson correlation coefficient, R-squared, for linear relationships with constant error variance, and has the intuitive meaning of the piecewise R-squared between the variables. It is particularly effective in handling nonlinearity and heteroscedastic errors. We propose two estimators of G-squared and show their consistency. Simulations demonstrate that G-squared estimators are among the most powerful test statistics compared with several state-of-the-art methods.
DOI: 10.1214/09-aoas312
发表时间: 2009-01-01
期刊: The annals of applied statistics
影响因子: --
作者:
Kosorok MR
通讯作者: Kosorok MR
DOI: 10.2307/2290860
发表时间: 1994-06-01
影响因子: 3.7
作者:
DOKSUM, K;BLYTH, S;ZHAO, HY
通讯作者: ZHAO, HY
DOI: 10.1214/aoms/1177730150
发表时间: 1948-01-01
影响因子: --
作者:
HOEFFDING, W
通讯作者: HOEFFDING, W
DOI: 10.1007/bf02595777
发表时间: 2004-12-01
期刊: TEST
影响因子: 1.3
作者:
Genest, C;Rémillard, B
通讯作者: Rémillard, B
DOI: 10.1103/physreve.69.066138
发表时间: 2004-06-01
期刊: PHYSICAL REVIEW E
影响因子: 2.4
作者:
Kraskov, A;Stögbauer, H;Grassberger, P
通讯作者: Grassberger, P