[R] ANOVA f-test

Prof Brian D Ripley ripley at stats.ox.ac.uk
Sun Mar 7 21:36:49 CET 1999

On Sun, 7 Mar 1999, Brian Kurotsuchi wrote:

> I have a rather basic question.  How can I get R to generate a ANOVA table
> and a f-value for a hypothesis test such as:

F-value, please. Named after {F}isher, I believe.
> Data: group1 values: 5.2 4.5 6.0 6.1 6.7 5.8
>       group2 values: 6.5 8.0 6.1 7.5 5.9 5.6
>       ...
> H0: mean1 = mean2 = mean3 = mean4

What are these: the means of four groups, two of which are shown?

> HA: at least two means different
> where I want to evaluate using a f test statistic?
> F = MSTr/MSE
> I'd like a table similar to one that Minitab would produce:
>         Df	 Sum Sq   Mean Sq   F value
> mean1
> mean2
> mean3
> Error

(I don't see MS_Tr in _that_ table.)

Try using aov(response ~ grouping, data=) and its summary method for the
conventional analysis. If you have a four-group one-way layout I have no
idea what the `MINITAB' table means statistically (nor do I recognize it
from my long-ago usage of MINITAB): each mean only has a meaningful line
when you know what else has been fitted, and one should be looking at
contrasts.  You can get something like this by mis-using anova.lm.

> Secondly, how can do a second evaluation using a multiple ANOVA compare using
> Tukey's procedure?

Eh?  That could mean several things. If you mean Tukey's method of multiple
comparisons, it is not currently available in R. (It is in recent versions
of S-PLUS.)  [John Tukey is one of the most prolific of statisticians ever:
"Tukey's procedure" is not at all precise.]

Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch

More information about the R-help mailing list