学术报告

报告人：贺华副教授(美国杜兰大学)

报告题目：Testing inflated zeros for Poisson regression models

报告时间：2018年06月14日（周四）上午9:00-10:00

报告地点：25教14楼报告厅

参加人员：教师、研究生、本科生

报告摘要：Excessive zeros in Poisson regression models are common in practice and may cause over-dispersion problem, and hence yields invalidate inference when Poisson regression models are fitted. In such cases, zero-inflated Poisson (ZIP) regression models may be applied. There is a large body of literature on ZIP models. However, methods for testing whether there are excessive zeros are less well developed. In this talk, we introduce a new approach for testing inflated zeros under the Poisson model and compare it with the Vuong test, Wald, score, and likelihood ratio tests through simulation studies. The tests are illustrated with two real data examples.

贺华老师1992年毕业于西南师范大学数学系，2003年在美国罗彻斯特大学(University of Rochester)获得硕士学位，2007年在罗彻斯特大学获得博士学位。目前贺华老师的主要研究兴趣在于因果推断、纵向数据分析、半参与非参数推断等。贺华老师目前已在Biostatistics、 Journal of Statistical Planning and Inference、 Journal of Nonparametric Statistics、Statistics in Medicine等SCI期刊上发表多篇学术论文。