Multivariate logistic models

被引：15

作者：

Qaqish, Bahjat F. ^{[1
]}

Ivanova, Anastasia ^{[1
]}

机构：

[1] Univ N Carolina, Dept Biostat, Chapel Hill, NC 27599 USA

来源：

BIOMETRIKA | 2006年 / 93卷 / 04期

关键词：

correlated binary observations; generalised-linear model; logistic regression; marginal model; multivariate categorical data; CONTINGENCY-TABLES; REGRESSION;

D O I：

10.1093/biomet/93.4.1011

中图分类号：

Q [生物科学];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

The multivariate logistic transform is a reparameterisation of cell probabilities in terms of marginal logistic contrasts. It is known that an arbitrary set of logistic contrasts may not correspond to a valid joint distribution. In this paper we present an efficient algorithm for detecting whether or not the inverse transform exists, and for computing it if it does.

引用

页码：1011 / 1017

页数：7

共 14 条

[1]

[Anonymous], 1992, A Course in Combinatorics

[2]

BARNDORFFNIELSE.O, 1978, INFORMATION EXPONENT

[3]

Bergsma WP, 2002, ANN STAT, V30, P140

[4] MODELING MULTIVARIATE BINARY DATA WITH ALTERNATING LOGISTIC REGRESSIONS [J].

CAREY, V ;

ZEGER, SL ;

DIGGLE, P .

BIOMETRIKA, 1993, 80 (03) :517-526

[5] Bounds for cell entries in contingency tables given marginal totals and decomposable graphs [J].

Dobra, A ;

Fienberg, SE .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2000, 97 (22) :11885-11892

[6]

Dobra A., 2001, STAT J UN EC COMMISS, V18, P363

[7] Joint regression and association modeling of longitudinal ordinal data [J].

Ekholm, A ;

Jokinen, J ;

McDonald, JW ;

Smith, PWF .

BIOMETRICS, 2003, 59 (04) :795-803

[8] Association models for a multivariate binary response [J].

Ekholm, A ;

McDonald, JW ;

Smith, PWF .

BIOMETRICS, 2000, 56 (03) :712-718

[9]

GLONEK GFV, 1995, J ROY STAT SOC B MET, V57, P533

[10] A class of regression models for multivariate categorical responses [J].

Glonek, GFV .

BIOMETRIKA, 1996, 83 (01) :15-28

← 1 2 →