Orthogonal parallel-flats designs for sn11 × sn22 mixed factorial experiments
✍ Scribed by C.T. Liao; H.K. Iyer
- Publisher
- Elsevier Science
- Year
- 1998
- Tongue
- English
- Weight
- 711 KB
- Volume
- 69
- Category
- Article
- ISSN
- 0378-3758
No coin nor oath required. For personal study only.
✦ Synopsis
Orthogonal factorial and fractional factorial designs are very popular in many experimental studies, particularly in industrial screening experiments. When an experimenter is able to specify the set of nonnegligible factorial effects, it is sometimes possible to obtain an orthogonal design belonging to the class of parallel-flats designs, that has a smaller run size than a suitable design from the class of classical fractional factorial designs of resolution III, IV or V, which are single-flat designs typically available from textbooks and published tables. Li (1991, Ph.D. Thesis, Colorado state university) and Srivastava and Li (1996, J. Statist. Plann. Inference 53, 261-283) provided a set of necessary and sufficient conditions for a parallel-flats design to be orthogonal for estimating a user-specified set of factorial effects for s" factorial experiments. In nl n 2 this paper, we extend the results to s 1 × s 2 factorial experiments, where the numbers of levels for the factors are primes. The results are illustrated with some examples. (~) 1998 Elsevier Science B.V. All rights reserved.