A hypothesis-testing approach toward identifying active contrasts

The problem of identifying the active contrasts in an unreplicated fractional factorial design is approached from a hypothesis-testing point of view. The null hypothesis that all contrasts are inactive is first tested and, if rejected, the active contrasts causing rejection are identified and estimated. The method is illustrated with examples from Box and Meyer, compared with the confidence-interval approach of Dong and Lenth, and found to be a worthy competitor.