When sample sizes are equal , the parameters of the alternative parameterization are restricted by . For unequal sample sizes, the most natural restriction is . Use this to show that What is E(MSTr) when H0 is true? [This expectation is correct if is replaced by the restriction (or any other single linear restriction on the ai

’s used to reduce the model to I independent parameters), but simplifies the algebra and yields natural estimates for the model parameters (in particular, .]