报告题目： That Prasad-Rao is Robust: Estimation of Mean Squared Prediction Error of Observed Best Predictor under Potential Model Misspecification
报 告 人： 蒋继明 教授 加利福尼亚大学戴维斯分校
报告时间： 2022年3月8日 9：00-10：00
报告地点： Zoom会议：203 271 7634 密码：20220118
会议链接：https://us02web.zoom.us/j/2032717634?pwd=RVpyeXZTMWZGQ2JsaTBPajFFL0dKdz09
校内联系人：韩月才 hanyc@jlu.edu.cn
报告摘要：This work is regarding robust small area estimation (SAE) in terms of measure of uncertainty. We consider estimation of the mean squared prediction error (MSPE) of the observed best predictor (OBP) in SAE under the Fay-Herriot model with potential model misspecification. Previously, it was thought that the traditional Prasad-Rao linearization method could not be used, because it is derived under the assumption that the underlying model is correctly specified. However, we show that when it comes to estimating the unconditional MSPE, the Prasad-Rao (PR) estimator, derived for estimating the MSPE of OBP assuming that the underlying model is correct, remains first-order unbiased even when the underlying model is misspecified in its mean function. A second-order unbiased estimator of the MSPE is derived by modifying the PR MSPE estimator. The PR and modified PR estimators also have much smaller variation compared to the existing MSPE estimators for OBP. The theoretical findings are supported by empirical results including simulation studies and real-data applications. This work is joint with Xiaohui Liu and Haiqiang Ma of the Jiangxi University of Finance and Economics.
报告人简介：蒋继明，加利福尼亚大学戴维斯分校统计系教授，主要研究领域为混合效应模型、模型选择、小区域估计、纵向数据分析、精准医学、大数据智能、统计遗传学/生物信息学、药代动力学和渐近理论。发表论文100余篇，大多数发表在The Annals of Statistics、 Journal of the American Statistical Association, Journal of the Royal Statistical Society, Series B 和 Biometrika等顶级统计和生物统计学期刊上，著有七本专著，包括Linear and Generalized Linear Mixed Models and Their Applications (Springer 2007; 2nd ed. 2021), Large Sample Techniques for Statistics (Springer 2010; 2nd ed. 2022), The Fence Methods (World Scientific 2015; joint with Nguyen), Asymptotic Analysis of Mixed Effects Models: Theory, Application, and Open Problems (Chapman & Hall/CRC, 2017), Robust Mixed Model Analysis (World Scientific 2019). 多次受邀参加相关领域的国际学术会议并作大会主旨报告，先后被选为Institute of Mathematical Statistics (IMS；数理统计学会)，American Association for the Advancement of Science (AAAS; 美国科学促进协会)，American Statistical Association (ASA；美国统计学会)，International Statistical Institute (ISI；国际统计研究院)等国际著名统计协会的Fellow，长期担任Journal of American Statistical Association、The Annals of Statistics等学术期刊的副主编，曾获得美国统计协会的杰出统计应用奖以及美国国家科学基金会和美国国立卫生研究院颁发的众多奖项。
