Hierarchical Latin Hypercube Sampling

被引：19

作者：

Garg, Vikram V. ^{[1
,2
]}

Stogner, Roy H. ^{[2
]}

机构：

[1] MIT, 77 Massachusetts Ave, Cambridge, MA 02139 USA

[2] Univ Texas Austin, ICES, 201 E 24th St, Austin, TX 78712 USA

来源：

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION | 2017年 / 112卷 / 518期

关键词：

Correlation reduction algorithms; Monte Carlo methods; Uncertainty quantification;

D O I：

10.1080/01621459.2016.1158717

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

Latin hypercube sampling (LHS) is a robust, scalable Monte Carlo method that is used in many areas of science and engineering. We present a new algorithm for generating hierarchic Latin hypercube sets (HLHS) that are recursively divisible into LHS subsets. Based on this new construction, we introduce a hierarchical incremental LHS (HILHS) method that allows the user to employ LHS in a flexibly incremental setting. This overcomes a drawback of many LHS schemes that require the entire sample set to be selected a priori, or only allow very large increments. We derive the sampling properties for HLHS designs and HILHS estimators. We also present numerical studies that showcase the flexible incrementation offered by HILHS.

引用

页码：673 / 682

页数：10

共 10 条

[1] Some large deviations results for Latin Hypercube sampling [J].

Drew, SS ;

Homem-de-Mello, T .

Proceedings of the 2005 Winter Simulation Conference, Vols 1-4, 2005, :673-681

[2] Latin hypercube sampling and the propagation of uncertainty in analyses of complex systems [J].

Helton, JC ;

Davis, FJ .

RELIABILITY ENGINEERING & SYSTEM SAFETY, 2003, 81 (01) :23-69

[3]

OWEN AB, 1992, J ROY STAT SOC B MET, V54, P541

[4]

Pleming J. B., 2005, P 46 AIAA ASME ASCE, P1

[5] Sliced Latin Hypercube Designs [J].

Qian, Peter Z. G. .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2012, 107 (497) :393-399

[6] Nested Latin hypercube designs [J].

Qian, Peter Z. G. .

BIOMETRIKA, 2009, 96 (04) :957-970

[7]

Robinson D. G., 2001, STRUCTURAL SAFETY RE, P249

[8] Extension of Latin hypercube samples with correlated variables [J].

Sallaberry, C. J. ;

Helton, J. C. ;

Hora, S. C. .

RELIABILITY ENGINEERING & SYSTEM SAFETY, 2008, 93 (07) :1047-1059

[9] LARGE SAMPLE PROPERTIES OF SIMULATIONS USING LATIN HYPERCUBE SAMPLING [J].

STEIN, M .

TECHNOMETRICS, 1987, 29 (02) :143-151

[10]

Xiong S, 2012, THESIS

← 1 →