期刊
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
卷 86, 期 11, 页码 2073-2088出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/00949655.2015.1100615
关键词
Skewed population; outliers; model-based approach; value modification; simple random sampling; winsorization
We evaluate the merits of estimators for right-skewed data which are motivated by a distributional assumption for the tail of the population. Our aim is to make a coherent account of estimators of this type already existing in the literature as well as suggesting some modifications, and to compare their performance empirically to other conceivable alternatives. Our results indicate that making use of parametric models to derive the explicit form of estimators can be a fruitful approach for a wide range of right-skewed populations when auxiliary data is not available, especially for small samples.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据