ANCOVA: a heteroscedastic global test when there is curvature and two covariates

DOI10.1007/S00180-015-0640-4zbMATH Open1348.65042arXiv1509.00103OpenAlexW1943690327MaRDI QIDQ333398FDOQ333398

Publication date: 28 October 2016

Published in: Computational Statistics (Search for Journal in Brave)

Abstract: For two independent groups, let

M_{j} (m a t h b f X)

be some conditional measure of location for the

j

th group associated with some random variable

Y

given

m a t h b f X = (X_{1}, X_{2})

. Let

O m e g a = m a t h b f X_{1}, l d o t s, m a t h b f X_{K}

be a set of

K

points to be determined. An extant technique can be used to test

H_{0}

:

M_{1} (m a t h b f X) = M_{2} (m a t h b f X)

for each

m a t h b f X i n O m e g a

without making any parametric assumption about

M_{j} (m a t h b f X)

. But there are two general reasons to suspect that the method can have relatively low power. The paper reports simulation results on an alternative approach that is designed to test the global hypothesis

H_{0}

:

M_{1} (m a t h b f X) = M_{2} (m a t h b f X)

for all

m a t h b f X i n O m e g a

. The main result is that the new method offers a distinct power advantage. Using data from the Well Elderly 2 study, it is illustrated that the alternative method can make a practical difference in terms of detecting a difference between two groups.

Full work available at URL: https://arxiv.org/abs/1509.00103

zbMATH Keywords

trimmed mean ANCOVA smoothers Well Elderly 2 study

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Nonparametric regression and quantile regression (62G08)

Cites Work

Cited In (1)

ANCOVA: an approach based on a robust heteroscedastic measure of effect size

Uses Software

This page was built for publication: ANCOVA: a heteroscedastic global test when there is curvature and two covariates

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q333398)