报告摘要：The likelihood function plays a key role in the classical statistical inference.  However, for large data sets with complex structures, the traditional approach faces serious challenges. In this talk, we review the classical likelihood method. We also introduce a very useful likelihood inference method called weighted likelihood that combines information from all relevant sources. It can be viewed as an approximate Bayesian inference. We also derive the now commonly used composite likelihood as the optimal function under functional constraints. We will also discuss their applications in big data.

        报告人简介： Dr. Wang is a full professor in Statistics at the Department of Mathematics and Statistics of York University. He earned his Ph.D. in Statistics from University of British Columbia in 1996. He did one year postdoc on Data Mining from 2001-2002. He joined York University as an Assistant Professor in 2002. His research include likelihood inference, optimization, disease modelling, bioinformatics, data mining and big data.

        欢迎感兴趣的师生参加！