Abstract: | We consider the one-way classification random model. Using a measure of unbalancedness some MINQ-Estimation procedures and ANOVA-procedure have been investigated with respect to their sensibility to unbalancedness. Further if we define the efficiency of a design N as the ratio of the MSE (.)'s of the balanced and the unbalanced case we obtain for three MINQE-procedures upper and lower bounds of the minimum efficiency. |