[R] Anova - interpretation of the interaction term

[(Ted Harding)]

On 22-Apr-05 michael watson \(IAH-C\) wrote:
> [...]
> So from a statistical point of view, I can see exactly why the
> interaction term is significant, but what my colleage wants to know is
> that WITHIN the vaccinated group, does infection decrease expression
> significantly?  And within the unvaccinated group, does infection
> decrease expression significantly?  Etc etc etc  Can I get this
> information from the output of the ANOVA, or do I carry out a separate
> test on e.g. just the vaccinated group? (seems a cop out to me)

If I understand right, each of these questions can only be answered
in terms of the changes in mean level *within* group.

However, you are entitled to use the residual sum of squares
(after estimating both effects and interaction) for the estimate
of SE to which you compare these within-group changes. Provided,
of course, that the variance is homogenous across groups (i.e.
treatment and/or infection has no influence on variability).

You can get the latter from the original ANOVA (interaction term
included) but I think you should get the difference of means
(infected vs non-infected) by a separate anlysis of each group.

> Many thanks, and sorry, but it's Friday.

Don't apologise. Not your fault it's Friday. (Who *can* I blame?)

Cheers,
Ted.


--------------------------------------------------------------------
E-Mail: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk>
Fax-to-email: +44 (0)870 094 0861
Date: 22-Apr-05                                       Time: 11:52:40
------------------------------ XFMail ------------------------------