[R] Type II ANOVA for user-defined contrasts with covariates

John Fox jfox at mcmaster.ca
Tue Jul 10 03:22:50 CEST 2012


Dear Jordan,

Oddly, essentially the same question was posed by someone else three days ago.

Because groups enters the model additively, the proper test for each contrast is just the t-test for the corresponding coefficient in the summary()  for the model.

I hope this helps,
 John

------------------------------------------------
John Fox
Sen. William McMaster Prof. of Social Statistics
Department of Sociology
McMaster University
Hamilton, Ontario, Canada
http://socserv.mcmaster.ca/jfox

On Mon, 9 Jul 2012 20:06:22 +0100
 Jordan Ramsey <jmr201 at cam.ac.uk> wrote:
> I'm wondering if anyone would be able to help me out. I'm trying to use a
> type II ANOVA for a model with user-specified contrasts and covariates.
> 
> I have two treatment groups and a control group. I'm comparing average
> treatment to controls and also between the two treatment groups, but I'm
> also looking to adjust for age and gender as covariates:
> 
> contrastMat=cbind(c(-1,-1,2),c(1,-1,0))
> contrasts(groups)=contrastMat
> 
> Model=lm(Response~Age+Gender+Age:Gender+groups)
> 
> since I'm interested in SS(R | A,G,AG)
> 
> I was hoping then to use the Anova() function in the car() package to find
> the type II ANOVA for my specified contrasts, but when I do so it only
> looks at Response as a whole instead of the two contrasts. Any ideas where
> I'm going wrong?
> 
> Thanks,
> JR
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
/



More information about the R-help mailing list