RANDOMIZED SEARCH STRATEGIES FOR FINDING OPTIMAL OR NEAR OPTIMAL BLOCK AND ROW‐COLUMN DESIGNS
- 1 September 1993
- journal article
- Published by Wiley in Australian Journal of Statistics
- Vol. 35 (3) , 371-382
- https://doi.org/10.1111/j.1467-842x.1993.tb01345.x
Abstract
Summary: We consider a family of effective and efficient strategies for generating experimental designs of several types with high efficiency. These strategies employ randomized search directions and at some stages allow the possibility of taking steps in a direction of decreasing efficiency in an effort to avoid local optima. Hence our strategies have some affinity with the simulated annealing algorithm of combinatorial optimization. The methods work well and compare favourably with other search strategies. We have implemented them for incomplete block designs, optionally resolvable, and for row‐column designs.Keywords
This publication has 17 references indexed in Scilit:
- The Non-Orthogonal Design of ExperimentsJournal of the Royal Statistical Society Series A: Statistics in Society, 1990
- A REVIEW OF BOUNDS FOR THE EFFICIENCY FACTOR OF BLOCK DESIGNSAustralian Journal of Statistics, 1989
- Row-column α-designsBiometrika, 1986
- Algebra of a row-column designJournal of Statistical Planning and Inference, 1985
- On the construction of a class of efficient row-column designsJournal of Statistical Planning and Inference, 1985
- (M,S)-optimal row-column designsCommunications in Statistics - Theory and Methods, 1980
- On the Theory of Connected Designs: Characterization and OptimalityThe Annals of Statistics, 1974
- Factorization of the residual operator and canonical decomposition of nonorthogonal factors in the analysis of varianceBiometrika, 1971
- Optimality Criteria for Incomplete Block DesignsThe Annals of Mathematical Statistics, 1960
- The Efficiency Factor of an Incomplete Block DesignThe Annals of Mathematical Statistics, 1956