Partially-latinized designs

J. A. John; E. R. Williams

doi:10.1023/A:1008969914035

Partially-latinized designs

J. A. John^*, E. R. Williams

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

4 Citations (Scopus)

Abstract

An interchange optimization algorithm to construct partially-latinized designs is described. The objective function is a weighted linear combination of up to five functions, each of which corresponds to a blocking factor of the required design. Nested simulated annealing is used to address local optima problems. The average efficiency factors of the generated designs are assessed against theoretical upper bounds.

Original language	English
Pages (from-to)	203-207
Number of pages	5
Journal	Statistics and Computing
Volume	9
Issue number	3
DOIs	https://doi.org/10.1023/A:1008969914035
Publication status	Published - 1999
Externally published	Yes

Access to Document

10.1023/A:1008969914035

Cite this

@article{e719ef0a83ed4b1c96707682f310502e,

title = "Partially-latinized designs",

abstract = "An interchange optimization algorithm to construct partially-latinized designs is described. The objective function is a weighted linear combination of up to five functions, each of which corresponds to a blocking factor of the required design. Nested simulated annealing is used to address local optima problems. The average efficiency factors of the generated designs are assessed against theoretical upper bounds.",

keywords = "(M,S)-optimality, A-optimality, Average efficiency factor, Interchange algorithm, Latinized designs, Resolvable designs, Row-column designs, Simulated annealing, Upper bounds",

author = "John, \{J. A.\} and Williams, \{E. R.\}",

year = "1999",

doi = "10.1023/A:1008969914035",

language = "English",

volume = "9",

pages = "203--207",

journal = "Statistics and Computing",

issn = "0960-3174",

publisher = "Springer Netherlands",

number = "3",

}

TY - JOUR

T1 - Partially-latinized designs

AU - John, J. A.

AU - Williams, E. R.

PY - 1999

Y1 - 1999

N2 - An interchange optimization algorithm to construct partially-latinized designs is described. The objective function is a weighted linear combination of up to five functions, each of which corresponds to a blocking factor of the required design. Nested simulated annealing is used to address local optima problems. The average efficiency factors of the generated designs are assessed against theoretical upper bounds.

AB - An interchange optimization algorithm to construct partially-latinized designs is described. The objective function is a weighted linear combination of up to five functions, each of which corresponds to a blocking factor of the required design. Nested simulated annealing is used to address local optima problems. The average efficiency factors of the generated designs are assessed against theoretical upper bounds.

KW - (M,S)-optimality

KW - A-optimality

KW - Average efficiency factor

KW - Interchange algorithm

KW - Latinized designs

KW - Resolvable designs

KW - Row-column designs

KW - Simulated annealing

KW - Upper bounds

UR - https://www.scopus.com/pages/publications/0040172674

U2 - 10.1023/A:1008969914035

DO - 10.1023/A:1008969914035

M3 - Article

SN - 0960-3174

VL - 9

SP - 203

EP - 207

JO - Statistics and Computing

JF - Statistics and Computing

IS - 3

ER -

Partially-latinized designs

Abstract

Access to Document

Other files and links

Fingerprint

Cite this