Multiple comparison and two-way ANOVA design

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

Multiple comparison and two-way ANOVA design

Andrej Kastrin
Dear useRs,

I'm working on multiple comparison design on two factor (2 × 3 levels)
ANOVA. Each of the tests I have tried (Tukey, multcomp package) seem to
do only with one factor at a time.


fm1 <- aov(breaks ~ wool * tension, data = warpbreaks)
tHSD <- TukeyHSD(fm1, "tension", ordered = FALSE)

$tension
          diff       lwr        upr     p adj
M-L -10.000000 -19.35342 -0.6465793 0.0336262
H-L -14.722222 -24.07564 -5.3688015 0.0011218
H-M  -4.722222 -14.07564  4.6311985 0.4474210

I'm interested in posthoc comparisons between various levels of factor 1
and various levels of factor 2, both at the same time.
I know that is possible in SPSS, but... is there any R solution?

Cheers, Andrej

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Reply | Threaded
Open this post in threaded view
|

Re: Multiple comparison and two-way ANOVA design

Prof Brian Ripley
Did you read the TukeyHSD help page?  You chose to have one factor, so you
cannot blame R for your own choice.

Do be very careful that you understand what these so-called post hoc
tests do (and also what the main effect of a factor in the presence of an
interaction means, for in R it is not the same as in SPSS).

[It really isn't fair to send UTF-8 mail, and the formatting has gone
wrong en route to me (if it was ever right).  Plain text and wrapped lines
please.]

On Sun, 15 Jan 2006, Andrej Kastrin wrote:

> Dear useRs,
> I'm working on multiple comparison design on two factor (2 × 3 levels) ANOVA. Each of the tests I have tried (Tukey, multcomp package) seem to do only with one factor at a time.
>
> fm1 <- aov(breaks ~ wool * tension, data = warpbreaks)tHSD <- TukeyHSD(fm1, "tension", ordered = FALSE)
> $tension          diff       lwr        upr     p adjM-L -10.000000 -19.35342 -0.6465793 0.0336262H-L -14.722222 -24.07564 -5.3688015 0.0011218H-M  -4.722222 -14.07564  4.6311985 0.4474210
> I'm interested in posthoc comparisons between various levels of factor 1 and various levels of factor 2, both at the same time.I know that is possible in SPSS, but... is there any R solution?
> Cheers, Andrej
> [hidden email] mailing listhttps://stat.ethz.ch/mailman/listinfo/r-helpPLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
>

--
Brian D. Ripley,                  [hidden email]
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 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595
______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html