首页

当前您的位置: 首页 > 学术讲座 > 正文

Likelihood ratio tests in random graph models

发布日期:2024-06-20点击: 发布人:统计与数学学院

报告题目:Likelihood ratio tests in random graph models

主讲人:晏挺教授(华中师范大学)

时间:2024年7月11日(周四)16:30 p.m.

地点:北院卓远楼305会议室

主办单位:统计与数学学院


摘要:In this talk, we present likelihood ratio tests in some random graph models including the beta model for undirected graphs, the Bradley-Terry model for paired companions and the p0 model for directed graphs. For two growing dimensional null hypotheses- a specified null and a homogenous null, we reveal high dimensional Wilks' phenomena that the normalized log-likelihood ratio statistic converges in distribution to a standard normal distribution when the number of being tested parameters goes to infinity. For the homogenous null with a fixed number of parameters, we establish the Wilks-type theorem that the log-likelihood ratio test converges in distribution to a chi-square distribution as the number of nodes goes to infinity.


主讲人简介:

晏挺,男,40岁,华中师范大学数学与统计学院教授。中国科学技术大学博士毕业,曾在乔治华盛顿大学做博士后研究,主要从事网络数据分析和成对比较的研究工作,主持了包含优秀青年基金项目,面上项目等多项国家自然科学基金项目,在Annals of Statistics, Journal of the American Statistical Association, Biometrika,Journal of Machine Learning Research上等发表了多篇论文。


Baidu
map