[R] set type of SS in anova()

John Fox jfox at mcmaster.ca
Sat Jul 5 12:20:10 CEST 2008

Dear j.c.l.omms,

The Anova() function in the car package can compute so-called "type-II" and
"type-III" tests. When there are terms in the model that are marginal to
others (such as main effects marginal to interactions), type-III tests are
of questionable interest and have to be formulated carefully to test
sensible hypotheses. As well, since glm() with no family argument fits a
linear model with normal errors, it would be more usual in R to use lm().


John Fox, Professor
Department of Sociology
McMaster University
Hamilton, Ontario, Canada
web: socserv.mcmaster.ca/jfox

> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org]
> Behalf Of jeroenooms
> Sent: July-04-08 6:37 PM
> To: r-help at r-project.org
> Subject: [R] set type of SS in anova()
> When you use the 'general linear model' analysis in SPSS, the first result
> a table with all terms with F-tests and significance values for all IV's.
> uses  http://joyx.joensuu.fi/~ek/anova/sstypes.txt SS Type III , which has
> the advantage that the order in which the variables are added to the model
> does not matter, and therefore it is relatively objective.
> I would like to reproduce this output in R. However, when using
> anova(glm.object, test="F"), the F test shows "Terms added sequentially
> (first to last)". Because of this, the F values and p values of the terms
> depend on the sequence in which they were added. Eg: an anova() of
> glm(a~b+c) will give other results than glm(a~c+b).
> How can I specify the SS type of an anova in R, so that i can reproduce
> exact results as that i got in SPSS?
> --
> View this message in context: http://www.nabble.com/set-type-of-SS-in-
> anova%28%29-tp18287076p18287076.html
> Sent from the R help mailing list archive at Nabble.com.
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> and provide commented, minimal, self-contained, reproducible code.

More information about the R-help mailing list