Anyone out there a stats guru who can help me on a question about repeated measures ANOVA?

I have a two factor repeated measure (call it A) and my data can be split into either 2 independent groups or 3 independent groups. If I run two ANOVAs - one 2(A)X2 the other 2(A)x3, I'd expect the main effect of A to give the same result on the two ANOVAs as the same data has gone in, but it doesn't. Any idea why?

I always thought the main effct of A should be the difference between the two levels of A collapsed accross groups thus it shouldn't matter how I split the data into groups

I'd imagine its something to do with degrees of freedom. I'd just trust in SPSS and don't question it 8-)

My thoughts were that when A is split across three independent groups the group sizes change (ie get smaller) so the 'effect' may not be as statistically significant.  Also does the effect A seem more prominent in only 1 or 2 of the independent groups, so when you split it between 3 groups the significance changes.

However, just to add I am not a statistician and as it is early, my effective caffeine intake has not been reached yet  :p

Thanks for responses. Not sure I explained it well last night. In this analysis measure A is a within subjects measure with two factor. When I do the main effect of A it shouldn't matter if the rest of the ANOVA (the independent groups bit) is split into two groups or three groups and I am still comparing the same data withing subjects (A1 and A2).

does that make any more sense???