Optimal discrimination designs for multifactor experiments. (English) Zbl 0888.62077

Dette, Holger; Röder, Ingo

Ann. Stat. 25, No. 3, 1161-1175 (1997); correction ibid. 26, No. 1, 449 (1998).

Summary: Efficient designs are determined when T. W. Anderson’s [Ann. Math. Stat. 33, 255-265 (1962; Zbl 0124.09304)] procedure is applied in order to identify the degree of a multivariate polynomial regression model. It is shown that the optimal designs are very closely related to model robust designs which maximize a weighted \(p\)-mean of \(D\)-efficiencies. As a consequence we obtain designs with high efficiency for model discrimination and for the statistical analysis in the identified model.

MSC:

62K05	Optimal statistical designs
62J05	Linear regression; mixed models
62G10	Nonparametric hypothesis testing
62A01	Foundations and philosophical topics in statistics

Keywords:

D-optimality; multifactor experiments; model discrimination; permutation invariance

Citations:

Zbl 0124.09304