应院长邀请，美国加利福尼亚大学洛杉矶分校杰出教授，国际著名心理统计学大师Peter M. Bentler将在7月4晚7:00在数理学院309学术报告厅讲学，机会难得，欢迎踊跃参与！

讲学内容

下载信息  [文件大小：   下载次数： ]

点击浏览该文件:

此主题相关图片如下：

个人主页：http://www.psych.ucla.edu/Faculty/Bentler/

部分文献已经上载到统计所

同时还有下面的报告，欢迎师生踊跃参加，时间是7月4日晚8:00~8:30，我院统计方向的本科生和研究生今后均有机会去这两所学校留学（加州大学洛杉矶分校，圣母玛利亚大学）。

Normal Theory ML for Missing Data with Violation of Distribution Assumptions

Ke-Hai Yuan

University of Notre Dame

When missing data are either missing completely at random (MCAR) or missing
at random (MAR), the maximum likelihood (ML) estimation procedure preserves
many of its properties. However, in any statistical modeling, the
distribution specification for the likelihood function is at best only an
approximation to the real world, especially for higher-dimensional data. We
study the properties of the ML procedure based on the normal distribution
assumption when data are not normally distributed.
Specifically, we show that the normal distribution based ML estimate (MLE)
is still consistent and asymptotically normally distributed when the
missing data mechanism is MAR. When data are not missing at random, factors
that affect the asymptotic biases of the MLE are identified and discussed.
We also show that the commonly used sandwich-type covariance matrix is
still consistent when data are MAR. Our results indicate that formulas or
conclusions in the existing literature are not all correct.

Ke-Hai Yuan was trained as a statistician and is Associate Professor in
quantitative psychology at the University of Notre Dame. His research
interests are in the areas of psychometric theory and applied multivariate
statistics. He received the Cattell award for
early-career outstanding multivariate research from the Society of
Multivariate Experimental Psychology in 2002.

此主题相关图片如下：

报告如期在数理学院309会议室举行，报告结束后，还为部分学生进行了留学攻读美国心理学学位的咨询