Note on pairwise negative dependence of randomly shifted and jittered rank-1 lattices

Autor(en): Wnuk, Marcin
Gnewuch, Michael 
Stichwörter: Latin hypercube sampling; Lattice rules; Monte Carlo; Numerical integration; Operations Research & Management Science; Randomized quasi-Monte Carlo; VARIANCE; Variance reduction
Erscheinungsdatum: 2020
Herausgeber: ELSEVIER
Journal: OPERATIONS RESEARCH LETTERS
Volumen: 48
Ausgabe: 4
Startseite: 410
Seitenende: 414
Zusammenfassung: 
In a recent paper Christiane Lemieux analyzed pairwise negative dependence property of sampling schemes. Using it she showed that scrambled (0, m, 2)-nets lead to randomized quasi-Monte Carlo estimators with variance no larger than the variance of Monte Carlo estimators for functions monotone in each variable. We establish that the same result holds in arbitrary dimension for a specific randomized point set based on rank-1 lattices and show that the details of the randomization are crucial for the property to hold. (C) 2020 Elsevier B.V. All rights reserved.
ISSN: 01676377
DOI: 10.1016/j.orl.2020.04.005

Show full item record

Page view(s)

8
Last Week
0
Last month
0
checked on Feb 29, 2024

Google ScholarTM

Check

Altmetric