Optimal cross-over designs for full interaction models.

R. A. Bailey (1, 2) , Pierre Druilhet (3)

1 QMUL - Queen Mary University of London
2 University of St Andrews [Scotland]
3 LMBP - Laboratoire de Mathématiques Blaise Pascal

We consider repeated measurement designs when a residual or carry-over effect may be present in at most one later period. To avoid too rough a model, we assume that there are interactions between carry-over and direct treatment effects. When the aim of the experiment is to study the effects of a treatment used alone, we obtain universally optimal approximate designs. We also propose some efficient designs with a reduced number of subjects.

Mots clés: Universal optimality; Approximate design; Neighbour design; Optimal design; Total effect; Universal optimality.

Domaines: Statistiques [math.ST]; Théorie [stat.TH]

R. A. Bailey, Pierre Druilhet. Optimal cross-over designs for full interaction models.. 2013. ⟨hal-00844298⟩