A matrix-valued Bernoulli distribution

Gianfranco Lovison

A matrix-valued Bernoulli distribution

Gianfranco Lovison

Scienze Economiche, Aziendali e Statistiche

Risultato della ricerca: Article › peer review

8 Citazioni (Scopus)

Abstract

Matrix-valued distributions are used in continuous multivariate analysis to model sample datamatrices of continuous measurements; their use seems to be neglected for binary, or more generallycategorical, data. In this paper we propose a matrix-valued Bernoullidistribution, based on the log-linear representation introducedby Cox (1972) for the Multivariate Bernoulli distribution with correlated components.

Lingua originale	English
pagine (da-a)	1573-1585
Numero di pagine	13
Rivista	Journal of Multivariate Analysis
Volume	97
Stato di pubblicazione	Published - 2006

All Science Journal Classification (ASJC) codes

Statistics and Probability
Numerical Analysis
Statistics, Probability and Uncertainty

Altri file e collegamenti

OA Link

Fingerprint Entra nei temi di ricerca di 'A matrix-valued Bernoulli distribution'. Insieme formano una fingerprint unica.

Cita questo

@article{1c94670661cd4abbb48468bc363be1cf,

title = "A matrix-valued Bernoulli distribution",

abstract = "Matrix-valued distributions are used in continuous multivariate analysis to model sample datamatrices of continuous measurements; their use seems to be neglected for binary, or more generallycategorical, data. In this paper we propose a matrix-valued Bernoullidistribution, based on the log-linear representation introducedby Cox (1972) for the Multivariate Bernoulli distribution with correlated components.",

author = "Gianfranco Lovison",

year = "2006",

language = "English",

volume = "97",

pages = "1573--1585",

journal = "Journal of Multivariate Analysis",

issn = "0047-259X",

publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - A matrix-valued Bernoulli distribution

AU - Lovison, Gianfranco

PY - 2006

Y1 - 2006

N2 - Matrix-valued distributions are used in continuous multivariate analysis to model sample datamatrices of continuous measurements; their use seems to be neglected for binary, or more generallycategorical, data. In this paper we propose a matrix-valued Bernoullidistribution, based on the log-linear representation introducedby Cox (1972) for the Multivariate Bernoulli distribution with correlated components.

AB - Matrix-valued distributions are used in continuous multivariate analysis to model sample datamatrices of continuous measurements; their use seems to be neglected for binary, or more generallycategorical, data. In this paper we propose a matrix-valued Bernoullidistribution, based on the log-linear representation introducedby Cox (1972) for the Multivariate Bernoulli distribution with correlated components.

UR - http://hdl.handle.net/10447/26314

M3 - Article

VL - 97

SP - 1573

EP - 1585

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

ER -