ROBUSTNESS OF BALANCED FRACTIONAL 2(M) FACTORIAL-DESIGNS DERIVED FROM SIMPLE ARRAYS

This is a review of the robustness of balanced fractional 2m factorial designs derived from simple arrays, which contains two kinds of robustness. One is the robustness of designs against incomplete data in the sense that, when any observations are missing, all unknown effects are still estimable in the model assumed. The other is based on the measure of sensitivity in the sense that a design should be insensitive to wild observations.