CHARACTERIZATION OF BEST MODEL-BASED PREDICTORS IN SURVEY SAMPLING
成果类型：
Article
署名作者：
TAM, SM
刊物名称：
BIOMETRIKA
ISSN/ISSBN：
0006-3444
发表日期：
1986
页码：
232235
关键词：
摘要：
This paper presents the necessary and sufficient conditions for the optimality of an arbitrary linear predictor of the total of a finite population in survey sampling under a general linear model with a symmetric and positive-definite covariance matrix. Results of the paper extend and unify earlier work on robust estimation in survey sampling under more restrictive conditions.