Modification of the Maximin and phi(p) (Phi) Criteria to Achieve Statistically Uniform Distribution of Sampling Points

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26110%2F20%3APU134111" target="_blank" >RIV/00216305:26110/20:PU134111 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.tandfonline.com/doi/full/10.1080/00401706.2019.1639550" target="_blank" >https://www.tandfonline.com/doi/full/10.1080/00401706.2019.1639550</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1080/00401706.2019.1639550" target="_blank" >10.1080/00401706.2019.1639550</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Modification of the Maximin and phi(p) (Phi) Criteria to Achieve Statistically Uniform Distribution of Sampling Points

Popis výsledku v původním jazyce

This article proposes a sampling technique that delivers robust designs, that is, point sets selected from a design domain in the shape of a unit hypercube. The designs are guaranteed to provide a statistically uniform point distribution, meaning that every location has the same probability of being selected. Moreover, the designs are sample uniform, meaning that each individual design has its points spread evenly throughout the domain. The sample uniformity (often measured via a discrepancy criterion) is achieved using distance-based criteria ( or Maximin), that is, criteria normally used in space-filling designs. We show that the standard intersite metrics employed in distance-based criteria (Maximin and (phi)) do not deliver statistically uniform designs. Similarly, designs optimized via centered L-2 discrepancy or support points are also not statistically uniform. When these designs (after optimization based on intersite distances) are used for Monte Carlo type of integration, their statistical nonuniformity is a serious problem as it may lead to a systematic bias. This article proposes using a periodic metric to guarantee the statistical uniformity of the family of distance-based designs. The presented designs used as benchmarks in the article are only taken from the class of Latin hypercube designs, which forces univariate projections to be uniform and improves accuracy in Monte Carlo integration of some functions. for this article are available online.

Název v anglickém jazyce

Modification of the Maximin and phi(p) (Phi) Criteria to Achieve Statistically Uniform Distribution of Sampling Points

Popis výsledku anglicky

This article proposes a sampling technique that delivers robust designs, that is, point sets selected from a design domain in the shape of a unit hypercube. The designs are guaranteed to provide a statistically uniform point distribution, meaning that every location has the same probability of being selected. Moreover, the designs are sample uniform, meaning that each individual design has its points spread evenly throughout the domain. The sample uniformity (often measured via a discrepancy criterion) is achieved using distance-based criteria ( or Maximin), that is, criteria normally used in space-filling designs. We show that the standard intersite metrics employed in distance-based criteria (Maximin and (phi)) do not deliver statistically uniform designs. Similarly, designs optimized via centered L-2 discrepancy or support points are also not statistically uniform. When these designs (after optimization based on intersite distances) are used for Monte Carlo type of integration, their statistical nonuniformity is a serious problem as it may lead to a systematic bias. This article proposes using a periodic metric to guarantee the statistical uniformity of the family of distance-based designs. The presented designs used as benchmarks in the article are only taken from the class of Latin hypercube designs, which forces univariate projections to be uniform and improves accuracy in Monte Carlo integration of some functions. for this article are available online.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

<a href="/cs/project/GA16-22230S" target="_blank" >GA16-22230S: Rozvoj pokročilých simulačních metod pro statistickou analýzu konstrukcí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Technometrics

ISSN

0040-1706

e-ISSN

1537-2723

Svazek periodika

62

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

16

Strana od-do

371-386

Kód UT WoS článku

000484398500001

EID výsledku v databázi Scopus

2-s2.0-85071304878