Multivariate logistic regression for familial aggregation in age at disease onset

Abigail G. Matthews, Dianne M. Finkelstein, Rebecca Betensky

Research output: Contribution to journalArticle

Abstract

Familial aggregation studies seek to identify diseases that cluster in families. These studies are often carried out as a first step in the search for hereditary factors affecting the risk of disease. It is necessary to account for age at disease onset to avoid potential misclassification of family members who are disease-free at the time of study participation or who die before developing disease. This is especially true for late-onset diseases, such as prostate cancer or Alzheimer's disease. We propose a discrete time model that accounts for the age at disease onset and allows the familial association to vary with age and to be modified by covariates, such as pedigree relationship. The parameters of the model have interpretations as conditional log-odds and log-odds ratios, which can be viewed as discrete time conditional cross hazard ratios. These interpretations are appealing for cancer risk assessment. Properties of this model are explored in simulation studies, and the method is applied to a large family study of cancer conducted by the National Cancer Institute-sponsored Cancer Genetics Network (CGN).

Original languageEnglish (US)
Pages (from-to)191-209
Number of pages19
JournalLifetime Data Analysis
Volume13
Issue number2
DOIs
StatePublished - Jun 1 2007

Fingerprint

Multivariate Regression
Logistic Regression
Logistics
Aggregation
Agglomeration
Cancer
Pedigree
Genetic Network
Odds
Prostate Cancer
Alzheimer's Disease
Misclassification
Discrete-time Model
Odds Ratio
Risk Assessment
Hazard
Covariates
Risk assessment
Discrete-time
Die

Keywords

  • Age at onset
  • Cancer Genetics Network
  • Familial association

ASJC Scopus subject areas

  • Applied Mathematics

Cite this

Multivariate logistic regression for familial aggregation in age at disease onset. / Matthews, Abigail G.; Finkelstein, Dianne M.; Betensky, Rebecca.

In: Lifetime Data Analysis, Vol. 13, No. 2, 01.06.2007, p. 191-209.

Research output: Contribution to journalArticle

Matthews, Abigail G. ; Finkelstein, Dianne M. ; Betensky, Rebecca. / Multivariate logistic regression for familial aggregation in age at disease onset. In: Lifetime Data Analysis. 2007 ; Vol. 13, No. 2. pp. 191-209.
@article{a44b96790e0b46ecbb79b3aef9a0b877,
title = "Multivariate logistic regression for familial aggregation in age at disease onset",
abstract = "Familial aggregation studies seek to identify diseases that cluster in families. These studies are often carried out as a first step in the search for hereditary factors affecting the risk of disease. It is necessary to account for age at disease onset to avoid potential misclassification of family members who are disease-free at the time of study participation or who die before developing disease. This is especially true for late-onset diseases, such as prostate cancer or Alzheimer's disease. We propose a discrete time model that accounts for the age at disease onset and allows the familial association to vary with age and to be modified by covariates, such as pedigree relationship. The parameters of the model have interpretations as conditional log-odds and log-odds ratios, which can be viewed as discrete time conditional cross hazard ratios. These interpretations are appealing for cancer risk assessment. Properties of this model are explored in simulation studies, and the method is applied to a large family study of cancer conducted by the National Cancer Institute-sponsored Cancer Genetics Network (CGN).",
keywords = "Age at onset, Cancer Genetics Network, Familial association",
author = "Matthews, {Abigail G.} and Finkelstein, {Dianne M.} and Rebecca Betensky",
year = "2007",
month = "6",
day = "1",
doi = "10.1007/s10985-007-9037-1",
language = "English (US)",
volume = "13",
pages = "191--209",
journal = "Lifetime Data Analysis",
issn = "1380-7870",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Multivariate logistic regression for familial aggregation in age at disease onset

AU - Matthews, Abigail G.

AU - Finkelstein, Dianne M.

AU - Betensky, Rebecca

PY - 2007/6/1

Y1 - 2007/6/1

N2 - Familial aggregation studies seek to identify diseases that cluster in families. These studies are often carried out as a first step in the search for hereditary factors affecting the risk of disease. It is necessary to account for age at disease onset to avoid potential misclassification of family members who are disease-free at the time of study participation or who die before developing disease. This is especially true for late-onset diseases, such as prostate cancer or Alzheimer's disease. We propose a discrete time model that accounts for the age at disease onset and allows the familial association to vary with age and to be modified by covariates, such as pedigree relationship. The parameters of the model have interpretations as conditional log-odds and log-odds ratios, which can be viewed as discrete time conditional cross hazard ratios. These interpretations are appealing for cancer risk assessment. Properties of this model are explored in simulation studies, and the method is applied to a large family study of cancer conducted by the National Cancer Institute-sponsored Cancer Genetics Network (CGN).

AB - Familial aggregation studies seek to identify diseases that cluster in families. These studies are often carried out as a first step in the search for hereditary factors affecting the risk of disease. It is necessary to account for age at disease onset to avoid potential misclassification of family members who are disease-free at the time of study participation or who die before developing disease. This is especially true for late-onset diseases, such as prostate cancer or Alzheimer's disease. We propose a discrete time model that accounts for the age at disease onset and allows the familial association to vary with age and to be modified by covariates, such as pedigree relationship. The parameters of the model have interpretations as conditional log-odds and log-odds ratios, which can be viewed as discrete time conditional cross hazard ratios. These interpretations are appealing for cancer risk assessment. Properties of this model are explored in simulation studies, and the method is applied to a large family study of cancer conducted by the National Cancer Institute-sponsored Cancer Genetics Network (CGN).

KW - Age at onset

KW - Cancer Genetics Network

KW - Familial association

UR - http://www.scopus.com/inward/record.url?scp=34247363943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34247363943&partnerID=8YFLogxK

U2 - 10.1007/s10985-007-9037-1

DO - 10.1007/s10985-007-9037-1

M3 - Article

VL - 13

SP - 191

EP - 209

JO - Lifetime Data Analysis

JF - Lifetime Data Analysis

SN - 1380-7870

IS - 2

ER -