Nearly column-orthogonal designs based on leave-one-out good lattice point sets

Ru Yuan, Dennis K.J. Lin, Min Qian Liu

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Good lattice point sets have desirable space-filling properties, and many designs with large L1-distance can be obtained by the leave-one-out good lattice point method (Zhou and Xu, 2015). However, there are negatively fully correlated columns in such a design. This is undesirable in the modeling of computer experiments. To overcome such a deficiency, we propose a class of designs based on the leave-one-out good lattice point method, whose columns can be divided into two groups, such that any two columns are column-orthogonal when they are from different groups and nearly column-orthogonal when they are in the same group. The new designs can also estimate the linear effects without being correlated with the second-order effects. Moreover, they have good stratification properties and their L1-distances are comparable with the corresponding designs in Zhou and Xu (2015).

Original languageEnglish (US)
Pages (from-to)29-40
Number of pages12
JournalJournal of Statistical Planning and Inference
Volume185
DOIs
StatePublished - Jun 1 2017

Fingerprint

Orthogonal Design
Lattice Points
Point Sets
Computer Experiments
Stratification
Design
Modeling
Estimate
Experiments

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Cite this

@article{bede65ebfcaf4b5a8c486d1023eda296,
title = "Nearly column-orthogonal designs based on leave-one-out good lattice point sets",
abstract = "Good lattice point sets have desirable space-filling properties, and many designs with large L1-distance can be obtained by the leave-one-out good lattice point method (Zhou and Xu, 2015). However, there are negatively fully correlated columns in such a design. This is undesirable in the modeling of computer experiments. To overcome such a deficiency, we propose a class of designs based on the leave-one-out good lattice point method, whose columns can be divided into two groups, such that any two columns are column-orthogonal when they are from different groups and nearly column-orthogonal when they are in the same group. The new designs can also estimate the linear effects without being correlated with the second-order effects. Moreover, they have good stratification properties and their L1-distances are comparable with the corresponding designs in Zhou and Xu (2015).",
author = "Ru Yuan and Lin, {Dennis K.J.} and Liu, {Min Qian}",
year = "2017",
month = "6",
day = "1",
doi = "10.1016/j.jspi.2017.01.002",
language = "English (US)",
volume = "185",
pages = "29--40",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",

}

Nearly column-orthogonal designs based on leave-one-out good lattice point sets. / Yuan, Ru; Lin, Dennis K.J.; Liu, Min Qian.

In: Journal of Statistical Planning and Inference, Vol. 185, 01.06.2017, p. 29-40.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Nearly column-orthogonal designs based on leave-one-out good lattice point sets

AU - Yuan, Ru

AU - Lin, Dennis K.J.

AU - Liu, Min Qian

PY - 2017/6/1

Y1 - 2017/6/1

N2 - Good lattice point sets have desirable space-filling properties, and many designs with large L1-distance can be obtained by the leave-one-out good lattice point method (Zhou and Xu, 2015). However, there are negatively fully correlated columns in such a design. This is undesirable in the modeling of computer experiments. To overcome such a deficiency, we propose a class of designs based on the leave-one-out good lattice point method, whose columns can be divided into two groups, such that any two columns are column-orthogonal when they are from different groups and nearly column-orthogonal when they are in the same group. The new designs can also estimate the linear effects without being correlated with the second-order effects. Moreover, they have good stratification properties and their L1-distances are comparable with the corresponding designs in Zhou and Xu (2015).

AB - Good lattice point sets have desirable space-filling properties, and many designs with large L1-distance can be obtained by the leave-one-out good lattice point method (Zhou and Xu, 2015). However, there are negatively fully correlated columns in such a design. This is undesirable in the modeling of computer experiments. To overcome such a deficiency, we propose a class of designs based on the leave-one-out good lattice point method, whose columns can be divided into two groups, such that any two columns are column-orthogonal when they are from different groups and nearly column-orthogonal when they are in the same group. The new designs can also estimate the linear effects without being correlated with the second-order effects. Moreover, they have good stratification properties and their L1-distances are comparable with the corresponding designs in Zhou and Xu (2015).

UR - http://www.scopus.com/inward/record.url?scp=85011421268&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011421268&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2017.01.002

DO - 10.1016/j.jspi.2017.01.002

M3 - Article

AN - SCOPUS:85011421268

VL - 185

SP - 29

EP - 40

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

ER -