Formal Model (2 of 2)

---

Next section: Expected mean squares

The formal model shows that each score is assumed to be the sum of three components: the overall height or elevation of the scores (μ_g), the elevation or depression resulting from being in the jth population (μ_j), and error (ε_ij). In terms of this model, the null hypothesis tested by ANOVA is that all "a" values of α_j = 0. That is, each score is equal to the mean of the population means plus error.

Mathematical statisticians use the formal model in many of their derivations. An example is the derivation of the expected value of MSB.

Next section: Expected mean squares