| dc.contributor.author | Simiyu, Christine N | |
| dc.date.accessioned | 2013-09-26T06:12:49Z | |
| dc.date.available | 2013-09-26T06:12:49Z | |
| dc.date.issued | 2006 | |
| dc.identifier.citation | A project submitted to the school of Mathematics in partial fulfillment for the award of master of science degree in Statistics | en |
| dc.identifier.uri | http://erepository.uonbi.ac.ke:8080/xmlui/handle/123456789/56701 | |
| dc.description.abstract | Finite geometries are used in the construction of BIB and PBIB designs with
two and more than two-associate classes. Further, finite projective
geometries can also be used to construct fractional factorial designs for slevel
symmetrical factorial experiments; where s is a prime or a prime
power. Under a hierarchical model that includes the general mean, all main
effects and a specified set of two-factor interactions, the plans from finite
projective geometries have inter-effect orthogonality and are shown to be
universally optimal under a hierarchical model within the class of all plans
involving the same number of runs. Families of optimal plans from finite
projective geometries have been suggested. | en |
| dc.language.iso | en | en |
| dc.subject | Galois field, finite geometries, saturated designs, inter-effect orthogonality, universal optimality. | en |
| dc.title | Construction of Experimental Designs: A Finite Geometric Approach | en |
| dc.type | Thesis | en |
| local.publisher | School of Mathematics, University of Nairobi | en |
