[R] Two Different Interaction Terms for Mixed Factorial ANOVA in R?

[Richard M. Heiberger]

Angela,

My guess is that your data are not balanced.
That could be due to a typo in one of the factors, or it could be that
you actually have different numbers of observations at some of the
factor levels.

Rich

On Sun, May 17, 2015 at 12:05 PM, Angela Radulescu
<angela.radulescu at gmail.com> wrote:
> I have the following R output from a mixed factorial ANOVA:
>
> Error: subj
>                  Df Sum Sq Mean Sq F value  Pr(>F)   group
> 1   11.3   11.26   0.449 0.50811
> singleType        1    0.7    0.66   0.026 0.87220   group:singleType
> 1  237.5  237.53   9.484 0.00461 **Residuals        28  701.3   25.04
>                  ---Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05
> ‘.’ 0.1 ‘ ’ 1
> Error: subj:singleType
>                  Df Sum Sq Mean Sq F value Pr(>F)
> singleType        1 1566.4  1566.4 411.445 <2e-16 ***group:singleType
> 1    3.4     3.4   0.893  0.352    Residuals        30  114.2     3.8
>                  ---Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05
> ‘.’ 0.1 ‘ ’ 1
> Error: Within
>             Df Sum Sq Mean Sq F value Pr(>F)Residuals 3286   5747   1.749
>
> Here "group" is the between factor (2 levels) and "singleType" the within
> factor (2 levels). I'm not sure why there are two group:singleType
> interaction terms. Any help would be much appreciated!
>
> For reference, here is the original aov call:
>
> anova.p = aov(data = dat.colSingle, rt ~ (group*singleType) +
> Error(subj/singleType))
> summary(anova.p)
>
> Thank you!
>
> --
> Angela Radulescu
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.