A unified approach in addition or deletion of two level factorial designs

Evangelaras, H; Koukouvinos, C; Mantas, P

dc.contributor.author	Evangelaras, H	en
dc.contributor.author	Koukouvinos, C	en
dc.contributor.author	Mantas, P	en
dc.date.accessioned	2014-03-01T01:17:24Z
dc.date.available	2014-03-01T01:17:24Z
dc.date.issued	2002	en
dc.identifier.issn	0167-7152	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/14514
dc.subject	A-optimality	en
dc.subject	D-optimality	en
dc.subject	Fractional factorial	en
dc.subject	Hadamard matrix	en
dc.subject	Resolution III design	en
dc.subject.classification	Statistics & Probability	en
dc.subject.other	OPTIMUM WEIGHING DESIGNS	en
dc.subject.other	CONSTRUCTION	en
dc.title	A unified approach in addition or deletion of two level factorial designs	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/S0167-7152(02)00111-6	en
heal.identifier.secondary	http://dx.doi.org/10.1016/S0167-7152(02)00111-6	en
heal.language	English	en
heal.publicationDate	2002	en
heal.abstract	Suppose it is desired to have an optimal resolution III fraction of a 2p factorial in n runs where n ≡ 1 (mod4) or n ≡ 3 (mod 4). If n ≡ 1 (mod 4), we have to decide if we should add a run in a n × p submatrix of a Hadamard matrix of order n, say Hn or, alternatively, if we should delete three runs from a (n + 4) × p submatrix of a Hadamard matrix of order n + 4, say Hn+4, in an optimal manner, respectively. Similarly, when n ≡ 3 (mod 4), we have to decide between optimally adding three more runs to a n × p submatrix of Hn or optimally deleting a single run from a (n + 4) × p submatrix of Hn+4. The question to be studied is whether both strategies give designs that are equally efficient in terms of a well defined optimality criterion. We show that, in both cases, for p = 3 both strategies give equally efficient designs under the D- or the A-optimality criterion. When n ≡ 1 (mod 4) and p > 3, both criteria show that the ""addition"" design is always better than the ""deletion"" design. However, when n ≡ 3 (mod 4) and p > 3, the choice of the most efficient design varies as p enlarges. © 2002 Published by Elsevier Science B.V.	en
heal.publisher	ELSEVIER SCIENCE BV	en
heal.journalName	Statistics and Probability Letters	en
dc.identifier.doi	10.1016/S0167-7152(02)00111-6	en
dc.identifier.isi	ISI:000177915600002	en
dc.identifier.volume	59	en
dc.identifier.issue	1	en
dc.identifier.spage	125	en
dc.identifier.epage	133	en