Menelaos Stavrinides
2007-Oct-11 17:24 UTC
[R] Type III sum of squares and appropriate contrasts
I am running a two-way anova with Type III sums of squares and would like to be able to understand what the different SS mean when I use different contrasts, e.g. treatment contrasts vs helmert contrasts. I have read John Fox's "An R and S-Plus Companion to Applied Regression" approach -p. 140- suggesting that treatment contrasts do not usually result in meaningful results with Type III SS but it's not clear to me why. Any suggestions on a stats text discussing this would be greatly appreciated. Thanks, Mel -- Menelaos Stavrinides Ph.D. Candidate Environmental Science, Policy and Management 137 Mulford Hall MC #3114 University of California Berkeley, CA 94720-3114 USA Tel: 510 717 5249
On Thu, 2007-10-11 at 10:24 -0700, Menelaos Stavrinides wrote:> I am running a two-way anova with Type III sums of squares and would > like to be able to understand what the different SS mean when I use > different contrasts, e.g. treatment contrasts vs helmert contrasts. I > have read John Fox's "An R and S-Plus Companion to Applied Regression" > approach -p. 140- suggesting that treatment contrasts do not usually > result in meaningful results with Type III SS but it's not clear to me > why. Any suggestions on a stats text discussing this would be greatly > appreciated. > Thanks, > MelA good place to start would be Prof. Venables' "Exegeses on Linear Models": www.stats.ox.ac.uk/pub/MASS3/Exegeses.pdf Searching the r-help archives will also yield many discussions. Also, see R FAQ 7.18. HTH, Marc Schwartz
Using type III sums of squares with non-orthogonal contrasts is like the
classic grade school puzzle:
"3 men decide to share a hotel room that costs $30, so each pays $10.
The maneger realizes that the room they received is only $25 and sends
$5 back with the bellboy. The bellboy realizes that there is no good
way to split $5 3 ways decides to help them all by giving each man $1
and keeping $2 for himself. So each man has now paid $9 for a total of
$27, add the $2 that the bellboy kept and you get $29, but the original
total was $30. Where is the missing $1?"
It may also be enlightening to load the fortunes package and type:
fortune("III") several times.
--
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
greg.snow at intermountainmail.org
(801) 408-8111
> -----Original Message-----
> From: r-help-bounces at r-project.org
> [mailto:r-help-bounces at r-project.org] On Behalf Of Menelaos
> Stavrinides
> Sent: Thursday, October 11, 2007 11:24 AM
> To: r-help at r-project.org
> Subject: [R] Type III sum of squares and appropriate contrasts
>
> I am running a two-way anova with Type III sums of squares
> and would like to be able to understand what the different SS
> mean when I use different contrasts, e.g. treatment contrasts
> vs helmert contrasts. I have read John Fox's "An R and S-Plus
> Companion to Applied Regression"
> approach -p. 140- suggesting that treatment contrasts do not
> usually result in meaningful results with Type III SS but
> it's not clear to me why. Any suggestions on a stats text
> discussing this would be greatly appreciated.
> Thanks,
> Mel
>
> --
> Menelaos Stavrinides
> Ph.D. Candidate
> Environmental Science, Policy and Management
> 137 Mulford Hall MC #3114
> University of California
> Berkeley, CA 94720-3114 USA
> Tel: 510 717 5249
>
> ______________________________________________
> 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.
>