...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Quality Control and Applied Statistics >A kernel smoothing method of adjusting for unit nomesponse in sample surveys
【24h】

A kernel smoothing method of adjusting for unit nomesponse in sample surveys

机译：样本调查中调整单位点响应的核平滑方法

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

To address the problem of unit nonresponse in sample surveys by considering a weighting adjustment that divides the sampling weights by the reciprocal of estimates for response probabilities. The estimated response probabilities are obtained by kernel regression, a procedure that avoids prespecifying a parametric form for the nonresponse model. Nonresponse is a common problem in survey sampling, and this phenomenon can only be ignored at the risk of invalidating inferences from a survey. A wide range of procedures is available to compensate for missing data. Kalton and Kasprzyk (Ref. 1) classify such procedures as weighting adjustments and imputation techniques. Weighting adjustments are used to compensate for unit nonresponse, which occurs when no value for the characteristics of interest is recorded for the unit. These adjustments increase the weights of the units that respond to the survey in order to compensate for those who do not. Imputation techniques, on the other hand, are most often intended to handle item nonresponse, which occurs when there is partial data collection for some items of a given unit. The authors will consider the case of unit nonresponse in this article.
机译：为了解决抽样调查中单位不响应的问题，可以考虑采用加权调整，该加权调整将采样权重除以响应概率的估计值的倒数。估计的响应概率是通过内核回归获得的，该过程避免为非响应模型预先指定参数形式。无响应是调查抽样中的常见问题，只有在使调查推论无效的风险下，才能忽略这种现象。可以使用多种程序来补偿丢失的数据。 Kalton和Kasprzyk（参考文献1）对诸如加权调整和插补技术之类的程序进行了分类。加权调整用于补偿单元无响应，这种响应在没有为单元记录感兴趣特性的值时发生。这些调整增加了对调查做出响应的单位的权重，以补偿未做出响应的单位。另一方面，插补技术通常用于处理项目无响应，这种情况发生在给定单位的某些项目有部分数据收集时。作者将在本文中考虑单位无响应的情况。

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