...
首页> 外文期刊>Quality Control and Applied Statistics >A new variance estimator for a two-phase restratified sample with PPS sampling at both phases
【24h】

A new variance estimator for a two-phase restratified sample with PPS sampling at both phases

机译:两相经过再验证的样本在两阶段均采用PPS采样的新方差估计器

获取原文
获取原文并翻译 | 示例
           

摘要

The authors of this paper consider variance estimation for population totals and ratios in complex, cross-stratified surveys in which the ultimate sampling weights are random variables dependent on the first phase of sampling, Ernst (Ref. 1). Such designs are useful where, for reasons of cost or logistics, it is expedient to sample primary sample units (PSUs) within one dimension of the stratification (say area strata) and secondary units within the second dimension of the stratification (say industrial strata), the choice of secondary units being limited to the PSUs already selected. Existing methods for two-phase sampling do not appear to be readily applicable to their problem. One difficulty, the fact of one PSU per area stratum is frequently handled in practice by an ad hoc collapsed approach. They propose instead a model-based approach for the first phase variance component, and use a design-based approach for estimating the second-phase variance component, leading to an overall hybrid estimator.
机译:本文的作者考虑了复杂,交叉分层调查中总体总数和比率的方差估计,在这些调查中,最终抽样权重是随机变量,取决于抽样的第一阶段恩斯特(参考资料1)。如果出于成本或物流的原因,在分层的一个维度(例如区域层次)内对主要样本单位(PSU)进行抽样,而在分层的第二个维度(例如工业层次)内对次要单位进行抽样,则此类设计非常有用,辅助设备的选择仅限于已选择的PSU。用于两阶段采样的现有方法似乎不适用于它们的问题。在实践中,经常采用一种特殊的折叠方法来处理一个困难,即每个区域地层一个PSU的事实。他们提出了针对第一阶段方差分量的基于模型的方法,并使用基于设计的方法来估计第二阶段方差分量,从而产生了整体混合估计器。

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