A joint mean-correlation modeling approach for longitudinal zero-inflated count data
报 告 人:: 张伟平
报告地点:: 数学与统计学院四楼学术报告厅
报告时间:: 2017年04月16日星期日10:20-11:00
报告简介:

Longitudinal zero-inflated count data are widely encountered in many fields, while modeling the correlation between measurements for the same subject is more challenge due to the lack of suitable multivariate joint distributions. In this paper, we propose a novel approach by using copula in longitudinal zero-inflated regression model, solving both problems of specifying joint distribution and parsimoniously modeling correlations with no constraint. We then study the use of hyper-spherical coordinates to parametrize the correlation matrix in the copula in terms of a set of angles, effectively a new set of constraint-free parameters on their support. Aided by this property, we propose separated mean and correlation regression models to understand these key quantities, which can also handle irregularly and possibly subject-specific times points. We show that the resulting estimators of the proposed approaches are consistent and asymptotically normal. Data example and simulations support the effectiveness of the proposed approach.

举办单位:数学与统计学院
发 布 人:科研助理 发布时间: 2017-04-17
主讲人简介:
张伟平,中国科学技术大学统计与金融系副教授。主要从事贝叶斯统计、纵向数据分析和统计模型理论及应用研究。先后主持多项国家自然科学基金项目,在纵向数据分析和Bayes统计方向的多项研究工作发表等国内外学术期刊上。