Hybrid Algorithms for Construction of D-Efficient Designs

Abdul Aziz Ali () and Magnus Jansson
Additional contact information
Abdul Aziz Ali: AstraZeneca R&D Södertälje, Clinical Information Management
Magnus Jansson: AstraZeneca R&D Södertälje, Clinical Information Management

A chapter in COMPSTAT 2004 — Proceedings in Computational Statistics, 2004, pp 37-48 from Springer

Abstract: Abstract We construct exact. D-efficient designs for linear regression models using a hybrid algorithm that consists of genetic and local search components. The genetic component is a genetic algorithm (GA) with a 100% mutation rate and ranking selection. The local search methods we use are based on the G-bit improvement and a combination of the Powel multidimensional and Brent line optimization techniques. Computational results show that the hybrid algorithm generates designs that are comparable in efficiency to those found using the modified Fedorov algorithm (MFA), but without being limited to using a given set of candidate points.

Keywords: Exact D-optimal designs; genetic algorithms; local search (search for similar items in EconPapers)
Date: 2004
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-7908-2656-2_2

Ordering information: This item can be ordered from
http://www.springer.com/9783790826562

DOI: 10.1007/978-3-7908-2656-2_2

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().