Testing conditional independence using maximal nonlinear conditional correlation
Abstract
In this paper, the maximal nonlinear conditional correlation of two random vectors and given another random vector , denoted by , is defined as a measure of conditional association, which satisfies certain desirable properties. When is continuous, a test for testing the conditional independence of and given is constructed based on the estimator of a weighted average of the form , where is the probability density function of and the 's are some points in the range of . Under some conditions, it is shown that the test statistic is asymptotically normal under conditional independence, and the test is consistent.
Cite
@article{arxiv.1010.3843,
title = {Testing conditional independence using maximal nonlinear conditional correlation},
author = {Tzee-Ming Huang},
journal= {arXiv preprint arXiv:1010.3843},
year = {2010}
}
Comments
Published in at http://dx.doi.org/10.1214/09-AOS770 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)