The Multivariate Ahrens Sampling Method

Roman Karawatzki

doi:10.57938/41ab04d6-e29d-43ee-bf97-fd442f771688

The Multivariate Ahrens Sampling Method

Roman Karawatzki

Institute for Statistics and Mathematics

Publication: Working/Discussion Paper › WU Working Paper

27 Downloads (Pure)

Abstract

The "Ahrens method" is a very simple method for sampling from univariate distributions. It is based on rejection from piecewise constant hat functions. It can be applied analogously to the multivariate case where hat functions are used that are constant on rectangular domains. In this paper we investigate the case of distributions with so called orthounimodal densities. Technical implementation details as well as their practical limitations are discussed. The application to more general distributions is considered. (author's abstract)

Original language	English
Place of Publication	Vienna
Publisher	Department of Statistics and Mathematics, WU Vienna University of Economics and Business
DOIs	https://doi.org/10.57938/41ab04d6-e29d-43ee-bf97-fd442f771688
Publication status	Published - 2006

Publication series

Series	Research Report Series / Department of Statistics and Mathematics
Number	30

WU Working Paper Series

Research Report Series / Department of Statistics and Mathematics

Access to Document

10.57938/41ab04d6-e29d-43ee-bf97-fd442f771688Licence: Unspecified

DocumentFinal published version, 612 KBLicence: Unspecified

Check availability

University Library Catalogue

Cite this

@techreport{41ab04d6e29d43eebf97fd442f771688,

title = "The Multivariate Ahrens Sampling Method",

abstract = "The {"}Ahrens method{"} is a very simple method for sampling from univariate distributions. It is based on rejection from piecewise constant hat functions. It can be applied analogously to the multivariate case where hat functions are used that are constant on rectangular domains. In this paper we investigate the case of distributions with so called orthounimodal densities. Technical implementation details as well as their practical limitations are discussed. The application to more general distributions is considered. (author's abstract)",

author = "Roman Karawatzki",

year = "2006",

doi = "10.57938/41ab04d6-e29d-43ee-bf97-fd442f771688",

language = "English",

series = "Research Report Series / Department of Statistics and Mathematics",

number = "30",

publisher = "Department of Statistics and Mathematics, WU Vienna University of Economics and Business",

edition = "March 2006",

type = "WorkingPaper",

institution = "Department of Statistics and Mathematics, WU Vienna University of Economics and Business",

}

TY - UNPB

T1 - The Multivariate Ahrens Sampling Method

AU - Karawatzki, Roman

PY - 2006

Y1 - 2006

N2 - The "Ahrens method" is a very simple method for sampling from univariate distributions. It is based on rejection from piecewise constant hat functions. It can be applied analogously to the multivariate case where hat functions are used that are constant on rectangular domains. In this paper we investigate the case of distributions with so called orthounimodal densities. Technical implementation details as well as their practical limitations are discussed. The application to more general distributions is considered. (author's abstract)

AB - The "Ahrens method" is a very simple method for sampling from univariate distributions. It is based on rejection from piecewise constant hat functions. It can be applied analogously to the multivariate case where hat functions are used that are constant on rectangular domains. In this paper we investigate the case of distributions with so called orthounimodal densities. Technical implementation details as well as their practical limitations are discussed. The application to more general distributions is considered. (author's abstract)

U2 - 10.57938/41ab04d6-e29d-43ee-bf97-fd442f771688

DO - 10.57938/41ab04d6-e29d-43ee-bf97-fd442f771688

M3 - WU Working Paper

T3 - Research Report Series / Department of Statistics and Mathematics

BT - The Multivariate Ahrens Sampling Method

PB - Department of Statistics and Mathematics, WU Vienna University of Economics and Business

CY - Vienna

ER -