Some Counterexamples Concerning Maximal Correlation and Linear Regression
Statistics Theory
2016-11-18 v2 Statistics Theory
Abstract
A class of examples concerning the relationship of linear regression and maximal correlation is provided. More precisely, these examples show that if two random variables have (strictly) linear regression on each other, then their maximal correlation is not necessarily equal to their (absolute) correlation.
Cite
@article{arxiv.1205.6248,
title = {Some Counterexamples Concerning Maximal Correlation and Linear Regression},
author = {Nickos Papadatos},
journal= {arXiv preprint arXiv:1205.6248},
year = {2016}
}
Comments
6 pages. Related to the 10th International Conference On Ordered Statistical Data And Their Applications (OSDA 2012), Murcia, Spain, 23-25 May 2012. Thanks are due to the Organizers, Jorge Navarro and F\'elix Belzunce, Universidad de Murcia, for their warm hospitality