科研交流
您的位置>>首页 > 科研交流 > 学术交流 > 阅读正文
科研交流

数学学院、所系列学术报告(701场):美国密苏里大学Hongyuan Cao教授

admin 发表于: 2017-06-07 08:33  点击:153
题  目:Analysis of longitudinal data with omitted asynchronous longitudinal  covariate
报告人:美国密苏里大学Hongyuan Cao教授
时  间:6月12日 上午10:00---12:00
地  点:数学楼629
摘要: Long term follow-up with longitudinal data is common in many medical investigations. In such studies, some longitudinal covariates can be omitted for various reasons. In cross sectional studies,  coefficient estimation of a covariate is unbiased if the covariate is orthogonal to the omitted covariate. This is not true in longitudinal data analysis, where omission of time dependent covariate can lead to biased coefficient estimate even if the corresponding covariate is orthogonal to the omitted longitudinal covariate. In this article, we propose a new unbiased estimation method to accommodate omitted longitudinal covariate. In addition, if the omitted longitudinal covariate is asynchronous with the longitudinal response, we propose a two stage approach for valid statistical inference. Asymptotic properties of the proposed parameter estimates are established. Extensive simulation studies provide numerical support for the theoretical findings. We illustrate the performance of our method on a dataset from an HIV study.