Re: correlations of ordered residuals with their expected values.
 From: "Anon." <bob.ohara@xxxxxxxxxxx>
 Date: Thu, 22 Feb 2007 07:50:57 +0200
Isabelle wrote:
I am working on a one way ANOVA. I am asked to do the following :
"compute the correlation between the ordered residuals and their
expected values under normality"
(this analysis appears to be related to the checking of the
assumption of normality of the residuals)
I know how to order the residuals. But I do not understand the part
about the expected value of the residuals under normality. I thought
that residuals were normally distributed about zero, which does not
make sense in these instructions.
Can anybody help me?
The residuals are ordered, so you're being asked about the expected value of the smallest, second smallest, etc. If you have two residuals, then the smallest of them will have an expected value less than zero (because the expected value of their sum is zero).
HTH
Bob

Bob O'Hara
Department of Mathematics and Statistics
P.O. Box 68 (Gustaf Hällströmin katu 2b)
FIN00014 University of Helsinki
Finland
Telephone: +3589191 51479
Mobile: +358 50 599 0540
Fax: +3589191 51400
WWW: http://www.RNI.Helsinki.FI/~boh/
Journal of Negative Results  EEB: www.jnreeb.org
.
 References:
 Prev by Date: Re: confused by "timevarying" and "timedependent" variables
 Next by Date: Re: a novice asks about ANOVA
 Previous by thread: correlations of ordered residuals with their expected values.
 Next by thread: Re: correlations of ordered residuals with their expected values.
 Index(es):
Relevant Pages
