I am trying to extract variance components for selection and chance in a bifactorial design with Generation as a fixed factor and Replicate as a random term, for early fecundity.
Since I am using the individual level (because I want to make confidence intervals for Chance), the sample size is not equal between Generations so it's an unbalanced design and it's is not a repeated measures ANOVA because my individuals are different.
The problem is that when I compare the results between Statistica and R the Mean Squares(MS) for the Generation and Replicate Factors are different (but the MS for Gen*Rep and the residuals are not!)
My data consist of 2 terms:
- Generation - 2 level fixed factor (6 and 11)
- Replicate - 3 level random factor (Ad1, Ad2, Ad3)
The model I am using is
g <- Anova (aov(Fec~ Gen+Rep+ Gen*Rep), random=~1|Gen*Rep)
I am not sure if this is how to phrase that I want the terms with Replicate to be random (maybe that's one of my errors when comparing with the Statistica results?).
Might the differences be due to the unbalanced design? Do R and Statistica have different ways of handling the different number of individuals in each replicate and generation?
Why aren't all MS equal? Is there a way to make the results be the same?
How can I indicate that a factor (and all its interactions) are random?
How can I tell R that I want it to test the Generation factor against the Gen*Rep term or to put it in another way to make it test the significance of the Gen factor against the heterogeneity between my replicates?