Open Access
Translator Disclaimer
2009 Testing for independence: Saddlepoint approximation to associated permutation distributions
Ehab F. Abd-Elfattah
Electron. J. Statist. 3: 625-632 (2009). DOI: 10.1214/09-EJS371


One of the most popular class of tests for independence between two random variables is the general class of rank statistics which are invariant under permutations. This class contains Spearman’s coefficient of rank correlation statistic, Fisher-Yates statistic, weighted Mann statistic and others. Under the null hypothesis of independence these test statistics have a permutation distribution that is usually approximated by using asymptotic normal theory to determine p-values for these tests. In this note we suggest using a saddlepoint approach that is almost exact and needs no simulations in order to calculate the p-value for tests in this class.


Download Citation

Ehab F. Abd-Elfattah. "Testing for independence: Saddlepoint approximation to associated permutation distributions." Electron. J. Statist. 3 625 - 632, 2009.


Published: 2009
First available in Project Euclid: 26 June 2009

zbMATH: 1326.62098
MathSciNet: MR2519534
Digital Object Identifier: 10.1214/09-EJS371

Keywords: independence tests , Linear rank test , permutation distribution , saddlepoint approximation

Rights: Copyright © 2009 The Institute of Mathematical Statistics and the Bernoulli Society


Back to Top