A Semi-nonparametric Approach to Joint Modeling of A Primary Binary Outcome and Longitudinal Data Measured at Discrete Informative Times

被引：2
作者：
Yan S. [1 ]
Zhang D. [1 ]
Lu W. [1 ]
Grifo J.A. [2 ]
Liu M. [3 ]
机构：
[1] Department of Statistics, North Carolina State University, Raleigh, NC
[2] NYU Fertility Center, NYU Langone Medical Center, NY, NY
[3] Division of Biostatistics, School of Medicine, New York University, NY, NY
来源：
Statistics in Biosciences | 2012年 / 4卷 / 2期
基金：
美国国家卫生研究院;
关键词：
EM algorithm; Informative observation times; IVF; Joint model; Longitudinal data; Maximum likelihood estimation; SNP density;
D O I：
10.1007/s12561-011-9053-2
中图分类号：
学科分类号：
摘要：
In a study conducted at the New York University Fertility Center, one of the scientific objectives is to investigate the relationship between the final pregnancy outcomes of participants receiving an in vitro fertilization (IVF) treatment and their β-human chorionic gonadotrophin (β-hCG) profiles. A common joint modeling approach to this objective is to use subject-specific normal random effects in a linear mixed model for longitudinal β-hCG data as predictors in a model (e. g., logistic model) for the final pregnancy outcome. Empirical data exploration indicates that the observation times for longitudinal β-hCG data may be informative and the distribution of random effects for longitudinal β-hCG data may not be normally distributed. We propose to introduce a third model in the joint model for the informative β-hCG observation times, and relax the normality distributional assumption of random effects using the semi-nonparametric (SNP) approach of Gallant and Nychka (Econometrica 55:363-390, 1987). An EM algorithm is developed for parameter estimation. Extensive simulation designed to evaluate the proposed method indicates that ignoring either informative observation times or distributional assumption of the random effects would lead to invalid and/or inefficient inference. Applying our new approach to the data reveals some interesting findings the traditional approach failed to discover. © 2012 International Chinese Statistical Association.
引用
收藏
页码：213 / 234
页数：21
相关论文
共 23 条
[1]  
Bjercke S., Tanbo T., Dale P.O., Morkrid L., Abyholm T., Human chorionic gonadotrophin concentrations in early pregnancy after in-vitro fertilization, Hum Reprod, 14, pp. 1642-1646, (1999)
[2]  
Chen H.Y., Little R.J.A., Proportional hazards regression with missing covariates, J Am Stat Assoc, 94, pp. 896-908, (1999)
[3]  
Chen J., Zhang D., Davidian M., A Monte Carlo EM algorithm for generalized linear mixed models with flexible random effects distribution, Biostatistics, 1, pp. 1-27, (2001)
[4]  
Chung K., Sammel M.D., Coutifaris C., Chalian R., Lin K., Castelbaum A.J., Freedman M.F., Barnhart K.T., Defining the rise of serum hCG in viable pregnancies achieved through use of IVF, Hum Reprod, 21, pp. 823-828, (2006)
[5]  
Confino E., Demir R.H., Friberg J., Gleicher N., The predictive value of hCG β subunit levels in pregnancies achieved by in vitro fertilization and embryo transfer: an international collaborative study, Fertil Steril, 45, pp. 526-531, (1986)
[6]  
Dempster A.P., Laird N.M., Rubin D.B., Maximum likelihood from incomplete data via the EM algorithm, J R Stat Soc, Ser B, Stat Methodol, 39, pp. 1-38, (1977)
[7]  
Gallant A.R., Nychka D.W., Seminonparametric maximum likelihood estimation, Econometrica, 55, pp. 363-390, (1987)
[8]  
Glatstein I.Z., Hornstein M.D., Kahana M.J., Jackson K.V., Friedman A.J., The predictive value of discriminatory human chorionic gonadotropin levels in the diagnosis of implantation outcome in vitro fertilization cycles, Fertil Steril, 63, pp. 350-356, (1995)
[9]  
Henderson R., Diggle P., Dobson A., Joint modelling of longitudinal measurements and event time data, Biostatistics, 1, pp. 465-480, (2000)
[10]  
Hogan J., Laird N., Model-based approaches to analysing incomplete longitudinal and failure time data, Stat Med, 16, pp. 259-272, (1997)
123