[R] An issue with White's test in Anova
jfox at mcmaster.ca
Sat Aug 25 01:12:29 CEST 2007
You've found a bug in Anova() for linear models that was introduced some
time ago when the linear.hypothesis() function [which is used by Anova()]
was modified not to report sums of squares for "White-adjusted" tests. I
have to think about should be done in this case.
John Fox, Professor
Department of Sociology
Canada L8S 4M4
> -----Original Message-----
> From: r-help-bounces at stat.math.ethz.ch
> [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of David Kaplan
> Sent: Friday, August 24, 2007 3:55 PM
> To: r-help at stat.math.ethz.ch
> Subject: [R] An issue with White's test in Anova
> Hi all,
> I'm running White's test to correct for non-constant error
> variance and I am using the Anova function in the package
> CAR. My command structure is
> > Anova(scireg3, white.adjust="hc3")
> where scireg3 is an object from lm.
> I get the message
> "Error in SS[i] <- SS.term(names[i]) : nothing to replace with"
> What does this mean and how do I fix it.
> Thanks in advance.
> David Kaplan, Ph.D.
> Department of Educational Psychology
> University of Wisconsin - Madison
> Educational Sciences, Room, 1061
> 1025 W. Johnson Street
> Madison, WI 53706
> email: dkaplan at education.wisc.edu
> Phone: 608-262-0836
> R-help at stat.math.ethz.ch mailing list
> PLEASE do read the posting guide
> and provide commented, minimal, self-contained, reproducible code.
More information about the R-help