[R] planned comparisons for ANOVA

Darren Weber darrenleeweber at gmail.com
Tue Jul 18 01:17:40 CEST 2006

On 7/17/06, Richard M. Heiberger <rmh at temple.edu> wrote:
> It looks to me like you are asking for the split= argument to
> the summary.aov method.  Look at ?summary.aov and the
> "# Cochran and Cox (1957, p.164)" example.
> I have more examples in my book
>                 Statistical Analysis and Data Display
>                 Richard M. Heiberger and Burt Holland
>                 http://springeronline.com/0-387-40270-5

Thanks for the additional advice.  At first glance, your book looks
good.  However, I have only taken undergraduate studies in statistics
(mostly taught by psychologists, not mathematicians), so the material
is most likely beyond my comprehension.  As a new user of R, it is
difficult to understand the methods and utilities.  The help pages are
consistent with most gnu/linux tools, they provide the essential
information, without much elaboration.  Most of the text books for R
are similar.  I am more familiar with stats texts in psychology, where
greater emphasis is placed on explanation (eg, Tabachnick & Fidell).

Anyhow, I can see now there are at least three utilities for contrasts
- the contrast option to aov, fit.contrast, summary.aov, and
estimable.  I don't have any clear rationale for using one or the
other.  I guess what I need to do now is generate a small example
dataset for which the planned comparison F values are known, to
validate the output of one or another of these routines.

Thanks, Darren

More information about the R-help mailing list