Simulating multivariate distributions with specific correlations

Abu T M Minhajuddin, Ian R. Harris, William R. Schucany

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

The mixture approach for simulating bivariate distributions introduced by Michael, J. R. and Schucany, W. R. (2002). The mixture approach for simulating bivariate distributions with specific correlations. The American Statistician, 56, 48-54, is generalized to generate pseudo-random numbers from multivariate distributions. The simulated joint distributions have identical marginals and equal positive painwise correlations. The approach is illustrated for the p-dimensional families of beta and gamma distributions. For these families the formulas for the correlations have simple closed forms and the computations are quite simple.

Original languageEnglish (US)
Pages (from-to)599-607
Number of pages9
JournalJournal of Statistical Computation and Simulation
Volume74
Issue number8
DOIs
StatePublished - Aug 2004

Fingerprint

Multivariate Distribution
Bivariate Distribution
Pseudorandom numbers
Beta distribution
Gamma distribution
Joint Distribution
Closed-form
Multivariate distribution
Family

Keywords

  • Beta distribution
  • Conjugate prior
  • Dependent
  • Exchangeable
  • Gamma distribution
  • Generating random variables
  • Joint distribution
  • Mixture method

ASJC Scopus subject areas

  • Applied Mathematics
  • Statistics and Probability
  • Modeling and Simulation

Cite this

Simulating multivariate distributions with specific correlations. / Minhajuddin, Abu T M; Harris, Ian R.; Schucany, William R.

In: Journal of Statistical Computation and Simulation, Vol. 74, No. 8, 08.2004, p. 599-607.

Research output: Contribution to journalArticle

@article{695d8cbab5e14ec5aa0bc39977a24347,
title = "Simulating multivariate distributions with specific correlations",
abstract = "The mixture approach for simulating bivariate distributions introduced by Michael, J. R. and Schucany, W. R. (2002). The mixture approach for simulating bivariate distributions with specific correlations. The American Statistician, 56, 48-54, is generalized to generate pseudo-random numbers from multivariate distributions. The simulated joint distributions have identical marginals and equal positive painwise correlations. The approach is illustrated for the p-dimensional families of beta and gamma distributions. For these families the formulas for the correlations have simple closed forms and the computations are quite simple.",
keywords = "Beta distribution, Conjugate prior, Dependent, Exchangeable, Gamma distribution, Generating random variables, Joint distribution, Mixture method",
author = "Minhajuddin, {Abu T M} and Harris, {Ian R.} and Schucany, {William R.}",
year = "2004",
month = "8",
doi = "10.1080/00949650310001626161",
language = "English (US)",
volume = "74",
pages = "599--607",
journal = "Journal of Statistical Computation and Simulation",
issn = "0094-9655",
publisher = "Taylor and Francis Ltd.",
number = "8",

}

TY - JOUR

T1 - Simulating multivariate distributions with specific correlations

AU - Minhajuddin, Abu T M

AU - Harris, Ian R.

AU - Schucany, William R.

PY - 2004/8

Y1 - 2004/8

N2 - The mixture approach for simulating bivariate distributions introduced by Michael, J. R. and Schucany, W. R. (2002). The mixture approach for simulating bivariate distributions with specific correlations. The American Statistician, 56, 48-54, is generalized to generate pseudo-random numbers from multivariate distributions. The simulated joint distributions have identical marginals and equal positive painwise correlations. The approach is illustrated for the p-dimensional families of beta and gamma distributions. For these families the formulas for the correlations have simple closed forms and the computations are quite simple.

AB - The mixture approach for simulating bivariate distributions introduced by Michael, J. R. and Schucany, W. R. (2002). The mixture approach for simulating bivariate distributions with specific correlations. The American Statistician, 56, 48-54, is generalized to generate pseudo-random numbers from multivariate distributions. The simulated joint distributions have identical marginals and equal positive painwise correlations. The approach is illustrated for the p-dimensional families of beta and gamma distributions. For these families the formulas for the correlations have simple closed forms and the computations are quite simple.

KW - Beta distribution

KW - Conjugate prior

KW - Dependent

KW - Exchangeable

KW - Gamma distribution

KW - Generating random variables

KW - Joint distribution

KW - Mixture method

UR - http://www.scopus.com/inward/record.url?scp=3042550046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3042550046&partnerID=8YFLogxK

U2 - 10.1080/00949650310001626161

DO - 10.1080/00949650310001626161

M3 - Article

AN - SCOPUS:3042550046

VL - 74

SP - 599

EP - 607

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 0094-9655

IS - 8

ER -