R help - Feb 2010 - split plot with aov

I have a factor SAMPLES which is at the lowest level (within) of a split plot
anova model  but this factor also appears in the ANOVA table at the block
level. This happens for unbalanced responses but not for balanced responses.
I would be grateful for an explanation of this.

The block error term is Day:Treatment:Temp and the within error term is
Day:Treatment:Temp:Samples.
Day is the main plot, Treatment the first split, Temp is within Treatment
and then Samples within Temp.

Thanks,
Penny B.




-- 
View this message in context:
http://n4.nabble.com/split-plot-with-aov-tp1472521p1472521.html
Sent from the R help mailing list archive at Nabble.com.

The dummy variables for the factors in balanced designs are orthogonal.
The treatment dummy variables are not orthogonal to the block dummy variables
for unbalanced designs.  That is essentially what the term "balanced"
means.