×

zbMATH — the first resource for mathematics

Construction results on minimum aberration blocking schemes for \(2^{m}\) designs. (English) Zbl 1120.62062
Summary: This paper considers constructing minimum aberration blocking schemes for \(2^{m}\) designs. A blocking scheme is said to have estimability of order \(e\) if \(e\) is the greatest integer such that no effect involving \(e\) or less factors is aliased with a block effect. We observe that a minimum aberration blocking scheme with estimability of order \(e\) uniquely corresponds to a minimum aberration design of resolution \(R=e+1\) and vice versa.
Two implications follow immediately from this result. First, all existing minimum aberration designs of resolution III or higher can be used to obtain minimum aberration blocking schemes with estimability of order 2 or higher. Second, resolution II designs of minimum aberration are now of both theoretical and practical importance as they provide solutions to minimum aberration blocking schemes with estimability of order 1. We study the construction of minimum aberration designs of resolution II, and obtain a complete solution to the problem.
MSC:
62K15 Factorial statistical designs
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] Block, R.M.; Mee, R.W., Resolution IV designs with 128 runs, J. qual. technol., 37, 282-293, (2005)
[2] Box, G.E.P.; Hunter, W.G.; Hunter, J.S., Statistics for experimenters, (1978), Wiley New York · Zbl 0394.62003
[3] Butler, N.A., Some theory for constructing minimum aberration fractional factorial designs, Biometrika, 90, 233-238, (2003) · Zbl 1034.62067
[4] Chen, H.; Cheng, C.S., Theory of optimal blocking of \(2^{n - m}\) designs, Ann. statist., 27, 1948-1973, (1999) · Zbl 0961.62066
[5] Chen, H.; Hedayat, A.S., \(2^{n - m}\) fractional factorial designs with (weak) minimum aberration, Ann. statist., 24, 2536-2548, (1996) · Zbl 0867.62066
[6] Chen, J., Some results on \(2^{n - k}\) fractional factorial designs and search for minimum aberration designs, Ann. statist., 20, 2124-2141, (1992) · Zbl 0770.62063
[7] Chen, J.; Wu, C.F.J., Some results on \(s^{n - k}\) fractional factorial designs with minimum aberration or optimal moments, Ann. statist., 19, 1028-1041, (1991) · Zbl 0725.62068
[8] Cheng, C.S.; Tang, B., A general theory of minimum aberration and its applications, Ann. statist., 33, 944-958, (2005) · Zbl 1068.62086
[9] Cheng, S.W.; Wu, C.F.J., Choice of optimal blocking schemes in two-level and three-level designs, Technometrics, 44, 269-277, (2002)
[10] Cheng, S.W.; Wu, C.F.J.; Wu, H., Finding defining generators with extreme lengths, J. statist. plann. inference, 113, 315-321, (2003) · Zbl 1039.62071
[11] Draper, N.R.; Lin, D.K.J., Capacity considerations for two-level fractional factorial designs, J. statist. plann. inference, 24, 25-35, (1990) · Zbl 0685.62059
[12] Sitter, R.R.; Chen, J.; Feder, M., Fractional resolution and minimum aberration in blocked \(2^{n - k}\) designs, Technometrics, 39, 382-390, (1997) · Zbl 0913.62073
[13] Suen, C.-Y.; Chen, H.; Wu, C.F.J., Some identities on \(q^{n - m}\) designs with application to minimum aberrations, Ann. statist., 25, 1176-1188, (1997) · Zbl 0898.62095
[14] Sun, D.X.; Wu, C.F.J.; Chen, Y., Optimal blocking schemes for \(2^n\) and \(2^{n - p}\) designs, Technometrics, 39, 298-307, (1997) · Zbl 0891.62055
[15] Tang, B.; Wu, C.F.J., Characterization of minimum aberration \(2^{n - k}\) designs in terms of their complementary designs, Ann. statist., 24, 2549-2559, (1996) · Zbl 0867.62068
[16] Wu, C.F.J.; Hamada, M., Experiments: planning, analysis, and parameter design optimization, (2000), Wiley New York · Zbl 0964.62065
[17] Xu, H., Minimum moment aberration for nonregular designs and supersaturated designs, Statist. sinica, 13, 691-708, (2003) · Zbl 1028.62063
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.