Matched survival data in a co-twin control design

Mette Gerster; Mia Madsen; Per Kragh Andersen

doi:10.1007/s10985-013-9256-6

Matched survival data in a co-twin control design

Mette Gerster, Mia Madsen, Per Kragh Andersen

Section of Biostatistics

5 Citations (Scopus)

Abstract

When using the co-twin control design for analysis of event times, one needs a model to address the possible within-pair association. One such model is the shared frailty model in which the random frailty variable creates the desired within-pair association. Standard inference for this model requires independence between the random effect and the covariates. We study how violations of this assumption affect inference for the regression coefficients and conclude that substantial bias may occur. We propose an alternative way of making inference for the regression parameters by using a fixed-effects models for survival in matched pairs. Fitting this model to data generated from the frailty model provides consistent and asymptotically normal estimates of regression coefficients, no matter whether the independence assumption is met.

Original language	English
Journal	Lifetime Data Analysis
Volume	20
Issue number	1
Pages (from-to)	38-50
Number of pages	13
ISSN	1380-7870
DOIs	https://doi.org/10.1007/s10985-013-9256-6
Publication status	Published - Jan 2014

Keywords

Bias (Epidemiology)
Computer Simulation
Humans
Models, Statistical
Research Design
Twin Studies as Topic

Access to Document

10.1007/s10985-013-9256-6

Cite this

@article{07f6ba4a71a243219ae883b49f8e695f,

title = "Matched survival data in a co-twin control design",

abstract = "When using the co-twin control design for analysis of event times, one needs a model to address the possible within-pair association. One such model is the shared frailty model in which the random frailty variable creates the desired within-pair association. Standard inference for this model requires independence between the random effect and the covariates. We study how violations of this assumption affect inference for the regression coefficients and conclude that substantial bias may occur. We propose an alternative way of making inference for the regression parameters by using a fixed-effects models for survival in matched pairs. Fitting this model to data generated from the frailty model provides consistent and asymptotically normal estimates of regression coefficients, no matter whether the independence assumption is met.",

keywords = "Bias (Epidemiology), Computer Simulation, Humans, Models, Statistical, Research Design, Twin Studies as Topic",

author = "Mette Gerster and Mia Madsen and Andersen, {Per Kragh}",

year = "2014",

month = jan,

doi = "10.1007/s10985-013-9256-6",

language = "English",

volume = "20",

pages = "38--50",

journal = "Lifetime Data Analysis",

issn = "1380-7870",

publisher = "Springer",

number = "1",

}

TY - JOUR

T1 - Matched survival data in a co-twin control design

AU - Gerster, Mette

AU - Madsen, Mia

AU - Andersen, Per Kragh

PY - 2014/1

Y1 - 2014/1

N2 - When using the co-twin control design for analysis of event times, one needs a model to address the possible within-pair association. One such model is the shared frailty model in which the random frailty variable creates the desired within-pair association. Standard inference for this model requires independence between the random effect and the covariates. We study how violations of this assumption affect inference for the regression coefficients and conclude that substantial bias may occur. We propose an alternative way of making inference for the regression parameters by using a fixed-effects models for survival in matched pairs. Fitting this model to data generated from the frailty model provides consistent and asymptotically normal estimates of regression coefficients, no matter whether the independence assumption is met.

AB - When using the co-twin control design for analysis of event times, one needs a model to address the possible within-pair association. One such model is the shared frailty model in which the random frailty variable creates the desired within-pair association. Standard inference for this model requires independence between the random effect and the covariates. We study how violations of this assumption affect inference for the regression coefficients and conclude that substantial bias may occur. We propose an alternative way of making inference for the regression parameters by using a fixed-effects models for survival in matched pairs. Fitting this model to data generated from the frailty model provides consistent and asymptotically normal estimates of regression coefficients, no matter whether the independence assumption is met.

KW - Bias (Epidemiology)

KW - Computer Simulation

KW - Humans

KW - Models, Statistical

KW - Research Design

KW - Twin Studies as Topic

U2 - 10.1007/s10985-013-9256-6

DO - 10.1007/s10985-013-9256-6

M3 - Journal article

C2 - 23864289

SN - 1380-7870

VL - 20

SP - 38

EP - 50

JO - Lifetime Data Analysis

JF - Lifetime Data Analysis

IS - 1

ER -

Matched survival data in a co-twin control design

Abstract

Keywords

Access to Document

Fingerprint

Cite this