[R] reporting ANOVA for nested models
daniel at umd.edu
Wed Sep 7 23:19:11 CEST 2011
fit1, the unrestricted model, includes 1 more regressor than fit2, the
restricted model. Testing the models against each other means that fit2 is
"equal to" fit1, assuming that the coefficient on the additional regressor
that is included in fit1 is restricted to zero.
Your F-test is thus whether this one extra regressor is significantly
different from zero, and the F-test is therefore on 1 and n-k degrees of
freedom, where 1 is the number of restrictions, n is the number of
observations and k is the number of coefficients in the unrestricted model.
So unless you do something a little more "spectacular" than just adding one
regressor and checking its significance, this is understood I would say.
That said, I am not a psychologist.
zugi young wrote:
> I have the following results for an ANOVA comparing two nested models. I
> wasn't sure how I am supposed to report this result in the area of
> psychology. Specifically, am I supposed to report the DF's or just the F
> ratio? I could manually calculate the degrees of freedoms, but there must
> a reason why R does not give this information, i.e. those are not
> conventionally used in the reporting?
> Any pointers would be greatly appreciated.
>> anova(fit1, fit2)
> Analysis of Variance Table
> Model 1: fit1
> Model 2: fit2
> Res.Df RSS Df Sum of Sq F Pr(>F)
> 1 373 19.908
> 2 374 30.717 -1 -10.809 202.53 < 2.2e-16 ***
> Signif. codes: 0 *** 0.001 ** 0.01 * 0.05 . 0.1 1
> [[alternative HTML version deleted]]
> R-help at r-project.org mailing list
> PLEASE do read the posting guide
> and provide commented, minimal, self-contained, reproducible code.
View this message in context: http://r.789695.n4.nabble.com/reporting-ANOVA-for-nested-models-tp3796957p3797302.html
Sent from the R help mailing list archive at Nabble.com.
More information about the R-help