Multivariate logistic regression for familial aggregation of two disorders. I. Development of models and methods

James I. Hudson, Nan M. Laird, Rebecca Betensky

Research output: Contribution to journalArticle

Abstract

The question of whether two disorders cluster together, or coaggregate, within families often arises. This paper considers how to analyze familial aggregation of two disorders and presents two multivariate logistic regression methods that model both disorder outcomes simultaneously. The first, a proband predictive model, predicts a relative's outcomes (the presence or absence of each of the two disorders) by using the proband's disorder status. The second, a family predictive model derived from the quadratic exponential model, predicts a family member's outcomes by using all of the remaining family members' disorder statuses. The models are more realistic, flexible, and powerful than univariate models. Methods for estimation and testing account for the correlation of outcomes among family members and can be implemented by using commercial software.

Original languageEnglish (US)
Pages (from-to)500-505
Number of pages6
JournalAmerican Journal of Epidemiology
Volume153
Issue number5
DOIs
StatePublished - Mar 1 2001

Fingerprint

Logistic Models
Software

Keywords

  • Family
  • Family characteristics
  • Generalized estimating equation
  • Logistic models

ASJC Scopus subject areas

  • Epidemiology

Cite this

Multivariate logistic regression for familial aggregation of two disorders. I. Development of models and methods. / Hudson, James I.; Laird, Nan M.; Betensky, Rebecca.

In: American Journal of Epidemiology, Vol. 153, No. 5, 01.03.2001, p. 500-505.

Research output: Contribution to journalArticle

Hudson, James I. ; Laird, Nan M. ; Betensky, Rebecca. / Multivariate logistic regression for familial aggregation of two disorders. I. Development of models and methods. In: American Journal of Epidemiology. 2001 ; Vol. 153, No. 5. pp. 500-505.
@article{b7a4291cd937472bb666cca3307cfc52,
title = "Multivariate logistic regression for familial aggregation of two disorders. I. Development of models and methods",
abstract = "The question of whether two disorders cluster together, or coaggregate, within families often arises. This paper considers how to analyze familial aggregation of two disorders and presents two multivariate logistic regression methods that model both disorder outcomes simultaneously. The first, a proband predictive model, predicts a relative's outcomes (the presence or absence of each of the two disorders) by using the proband's disorder status. The second, a family predictive model derived from the quadratic exponential model, predicts a family member's outcomes by using all of the remaining family members' disorder statuses. The models are more realistic, flexible, and powerful than univariate models. Methods for estimation and testing account for the correlation of outcomes among family members and can be implemented by using commercial software.",
keywords = "Family, Family characteristics, Generalized estimating equation, Logistic models",
author = "Hudson, {James I.} and Laird, {Nan M.} and Rebecca Betensky",
year = "2001",
month = "3",
day = "1",
doi = "10.1093/aje/153.5.500",
language = "English (US)",
volume = "153",
pages = "500--505",
journal = "American Journal of Epidemiology",
issn = "0002-9262",
publisher = "Oxford University Press",
number = "5",

}

TY - JOUR

T1 - Multivariate logistic regression for familial aggregation of two disorders. I. Development of models and methods

AU - Hudson, James I.

AU - Laird, Nan M.

AU - Betensky, Rebecca

PY - 2001/3/1

Y1 - 2001/3/1

N2 - The question of whether two disorders cluster together, or coaggregate, within families often arises. This paper considers how to analyze familial aggregation of two disorders and presents two multivariate logistic regression methods that model both disorder outcomes simultaneously. The first, a proband predictive model, predicts a relative's outcomes (the presence or absence of each of the two disorders) by using the proband's disorder status. The second, a family predictive model derived from the quadratic exponential model, predicts a family member's outcomes by using all of the remaining family members' disorder statuses. The models are more realistic, flexible, and powerful than univariate models. Methods for estimation and testing account for the correlation of outcomes among family members and can be implemented by using commercial software.

AB - The question of whether two disorders cluster together, or coaggregate, within families often arises. This paper considers how to analyze familial aggregation of two disorders and presents two multivariate logistic regression methods that model both disorder outcomes simultaneously. The first, a proband predictive model, predicts a relative's outcomes (the presence or absence of each of the two disorders) by using the proband's disorder status. The second, a family predictive model derived from the quadratic exponential model, predicts a family member's outcomes by using all of the remaining family members' disorder statuses. The models are more realistic, flexible, and powerful than univariate models. Methods for estimation and testing account for the correlation of outcomes among family members and can be implemented by using commercial software.

KW - Family

KW - Family characteristics

KW - Generalized estimating equation

KW - Logistic models

UR - http://www.scopus.com/inward/record.url?scp=0035283435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035283435&partnerID=8YFLogxK

U2 - 10.1093/aje/153.5.500

DO - 10.1093/aje/153.5.500

M3 - Article

VL - 153

SP - 500

EP - 505

JO - American Journal of Epidemiology

JF - American Journal of Epidemiology

SN - 0002-9262

IS - 5

ER -