TY - JOUR
T1 - Logistic regression when covariates are random effects from a non-linear mixed model
AU - De la Cruz, Rolando
AU - Marshall, Guillermo
AU - Quintana, Fernando A.
PY - 2011/9
Y1 - 2011/9
N2 - In many studies, the association of longitudinal measurements of a continuous response and a binary outcome are often of interest. A convenient framework for this type of problems is the joint model, which is formulated to investigate the association between a binary outcome and features of longitudinal measurements through a common set of latent random effects. The joint model, which is the focus of this article, is a logistic regression model with covariates defined as the individual-specific random effects in a non-linear mixed-effects model (NLMEM) for the longitudinal measurements. We discuss different estimation procedures, which include two-stage, best linear unbiased predictors, and various numerical integration techniques. The proposed methods are illustrated using a real data set where the objective is to study the association between longitudinal hormone levels and the pregnancy outcome in a group of young women. The numerical performance of the estimating methods is also evaluated by means of simulation.
AB - In many studies, the association of longitudinal measurements of a continuous response and a binary outcome are often of interest. A convenient framework for this type of problems is the joint model, which is formulated to investigate the association between a binary outcome and features of longitudinal measurements through a common set of latent random effects. The joint model, which is the focus of this article, is a logistic regression model with covariates defined as the individual-specific random effects in a non-linear mixed-effects model (NLMEM) for the longitudinal measurements. We discuss different estimation procedures, which include two-stage, best linear unbiased predictors, and various numerical integration techniques. The proposed methods are illustrated using a real data set where the objective is to study the association between longitudinal hormone levels and the pregnancy outcome in a group of young women. The numerical performance of the estimating methods is also evaluated by means of simulation.
KW - Best linear unbiased predictor (BLUP) and two-stage estimator
KW - Gaussian quadrature methods
KW - Laplace approximation
KW - Logistic regression model
KW - Non-linear mixed-effects models
UR - http://www.scopus.com/inward/record.url?scp=80052424255&partnerID=8YFLogxK
U2 - 10.1002/bimj.201000142
DO - 10.1002/bimj.201000142
M3 - Article
C2 - 21770044
AN - SCOPUS:80052424255
SN - 0323-3847
VL - 53
SP - 735
EP - 749
JO - Biometrical Journal
JF - Biometrical Journal
IS - 5
ER -