...
首页> 外文期刊>Quality Control and Applied Statistics >Comparison of estimation methods for the finite population mean in simple random sampling: Symmetric super populations
【24h】

Comparison of estimation methods for the finite population mean in simple random sampling: Symmetric super populations

机译:简单随机抽样中有限总体均值估计方法的比较:对称超总体

获取原文
获取原文并翻译 | 示例
           

摘要

Purpose: To propose a combined estimator for the finite mean Y-bar_N in SRS, assuming a long-tailed symmetric super-population model. Summary: The efficiency and robustness of the combined estimator are compared with the widely used estimators via Monte Carlo simulation. The estimators considered are least squares estimator, trimmed mean, Winsorized mean, trimmed L-mean, modified MLE, Huber estimator and nonparametric Hodgeslehmann estimator. Using the MSE criterion, the overall higher efficiency of combined estimator is demonstrated. Due to its insensitiveness to outliners and misspecification of distribution, the combined estimator is shown to be more robust. A real life example is included. (17 refs.)
机译:目的:假设长尾对称超种群模型,为SRS中的有限均值Y-bar_N提出一个组合估计量。摘要:通过蒙特卡洛模拟,将组合估计器的效率和鲁棒性与广泛使用的估计器进行了比较。所考虑的估计量是最小二乘估计量,修剪均值,Winsorized均值,修剪L均值,修正的MLE,Huber估计量和非参数Hodgeslehmann估计量。使用MSE准则,可以证明组合估计器的整体效率更高。由于其对轮廓绘制器不敏感并且分布不正确,因此组合估计量更加可靠。包括一个真实的例子。 (17个参考)

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号