Open AccessJoint mean-correlation model and its application to NorStOP binary data
Author(s) -
Peng Cheng,
Yihe Yang,
Jie Zhou,
Jianxin Pan
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1592/1/012077
Subject(s) - binary data , estimator , binary number , correlation , copula (linguistics) , gaussian , joint (building) , generalized estimating equation , mathematics , statistics , computer science , econometrics , engineering , physics , architectural engineering , geometry , arithmetic , quantum mechanics
In this paper we propose a generalized estimating equations method to joint model the mean and correlation structures for longitudinal binary data based on Gaussian copula, and apply it to a large cohort study for the UK’s North Staffordshire Osteoarthritis Project (NorStOP), where the responses can be pre-processed to binary variables. The resulting estimators for the mean and correlation parameters are proven to be consistent and asymptotically normally distributed. Since the theory and simulation results were studied in our previous manuscript [1], we give a brief introduction of our approach but mainly focus on its application to the NorStOP data.