基于空间误差分量Fay-Herriot模型的小域估计  

Spatial Error Component Fay-Herriot Models for Small Area Estimation

作　　者：李腾 魏传华[1] 苏宇楠[1] LI Teng;WEI Chuan-hua;SU Yu-nan(School of Science,Minzu University of China,Beijing 100081,China)

机构地区：[1]中央民族大学理学院,北京100081

出　　处：《统计与信息论坛》2018年第11期11-16,共6页Journal of Statistics and Information

基　　金：国家自然科学基金项目<复杂数据下半参数可加模型的统计推断>(11301565)

摘　　要：Fay-Herriot模型已在小域估计中得到了广泛应用,进而提出一类新的空间误差分量Fay-Herriot模型用以刻画空间效应。基于所提出的模型,给出小域目标参数的经验最佳线性无偏预测估计量;同时,还给出所提估计量对应均方误差的估计,并通过数值模拟验证所提方法的有效性。The Fay-Herriot model is widely used in small area estimation.This paper proposes a new spatial error component Fay-Herriot model to capture the spatially effects.An empirical best linear unbiased predictor(EBLUP)for small area parameters has been obtained under the proposed model,and an estimator of the mean squared prediction error of the EBLUP has also been given.Some simulations are conducted to examine the performance of the proposed estimators and the results are satisfactory.

关 键 词：Fay-Herriot模型 空间误差分量模型 小域估计 经验最佳线性无偏预测 

分 类 号：O212.1[理学—概率论与数理统计] C811[理学—数学]