WHEN ROBUST ESTIMATION IS NOT AN OBVIOUS ANSWER: THE CASE OF THE SYNTHETIC ESTIMATOR VERSUS ALTERNATIVES FOR SMALL AREAS
WHEN ROBUST ESTIMATION IS NOT AN OBVIOUS ANSWER: THE CASE OF THE SYNTHETIC ESTIMATOR VERSUS ALTERNATIVES FOR SMALL AREAS
复制标题
当稳健估计不是显而易见的答案时：小区域综合估计器与替代方案的案例
DOI：
--
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
C. Sarndal
中科院分区：
文献类型：
--
作者：
C. Sarndal
S untmary。综合估计和替代小面积估计进行了检查。一个强大的，近似无偏的替代开发，借用力量以同样的方式作为有偏合成估计。然而，小估计的特殊问题是这样的，它不是一个必然的结论，一个强大的方法应该采取优先于非强大的可能性。本文强调，估计方法的选择取决于一个复杂的相互作用的因素，包括样本大小，抽样比例，面积小，并从一个基本模型假设小面积的行为像大面积的偏离。
S untmary. The synthetic estimator and alternative small area estimators are examined. A robust, approximately unbiased alternative is developed that borrows strength in the same way as the biased synthetic estimator. However, the special problems of small estimation are such that it is not a foregone conclusion that a robust method should take precedent over non-robust possibilities. The paper emphasizes that the choice of estimation method depends on a complex interplay of factors, including sample size, sampling fraction, area smallness and departure from a basic model assuming that small areas behave like large areas.