Testing independence by nonparametric kernel method

被引：24

作者：

Ahmad, IA

Li, Q

机构：

[1] NO ILLINOIS UNIV,DIV STAT,DE KALB,IL 60115

[2] UNIV GUELPH,DEPT ECON,GUELPH,ON N1G 2W1,CANADA

来源：

STATISTICS & PROBABILITY LETTERS | 1997年 / 34卷 / 02期

关键词：

testing independence; kernel estimation; consistent tests; Monte Carlo simulation; asymptotic normality;

D O I：

10.1016/S0167-7152(96)00183-6

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

Using nonparametric kernel estimation method, we propose a consistent test for independence of two random vectors based on the L-2 norm of difference between the joint density and the product of their marginals. A Monte Carlo study is carried out to examine the finite sample performance of the proposed test.

引用

页码：201 / 210

页数：10

共 5 条

[1] NONPARAMETRIC-ESTIMATION OF THE LOCATION AND SCALE-PARAMETERS BASED ON DENSITY-ESTIMATION
AHMAD, IA
[J]. ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 1982, 34 (01) : 39 - 53
[2] Consistent model specification tests: Omitted variables and semiparametric functional forms
Fan, YQ
Li, Q
[J]. ECONOMETRICA, 1996, 64 (04) : 865 - 890
[3] CENTRAL LIMIT-THEOREM FOR INTEGRATED SQUARE ERROR OF MULTIVARIATE NONPARAMETRIC DENSITY ESTIMATORS
HALL, P
[J]. JOURNAL OF MULTIVARIATE ANALYSIS, 1984, 14 (01) : 1 - 16
[4] QUADRATIC MEASURE OF DEVIATION OF 2-DIMENSIONAL DENSITY ESTIMATES AND A TEST OF INDEPENDENCE
ROSENBLATT, M
[J]. ANNALS OF STATISTICS, 1975, 3 (01) : 1 - 14
[5] A NONPARAMETRIC MEASURE OF INDEPENDENCE UNDER A HYPOTHESIS OF INDEPENDENT COMPONENTS
ROSENBLATT, M
WAHLEN, BE
[J]. STATISTICS & PROBABILITY LETTERS, 1992, 15 (03) : 245 - 252

← 1 →