Model-Based Inference†

Model-Based Inference†
复制标题

基于模型的推理†

DOI:
10.1002/9780470057339.vam033
复制
发表时间:
2006
期刊:
影响因子:
2.5
通讯作者:
R. Chambers
R. Chambers
中科院分区:
生物学2区
文献类型:
--
作者:
R. Chambers

文献摘要

被引文献

相似文献

调查抽样中的一个基本问题是利用调查变量Y的样本数据来推断Y在抽样总体上的总和T的值。基于模型的方法来解决这个问题是基于一个联合的统计模型的Y的人口值,并在适当的情况下,抽样方法的推断。这与基于设计的抽样推断相反,其中不确定性的唯一来源是抽样方法的结果。
A basic problem in survey sampling is that of using the sample data for a survey variable Y to infer the value of the total T of Y over the sampled population. The model-based approach to this problem is to base this inference on a joint statistical model for both the population values of Y and, where appropriate, for the sampling method. This is in contrast to design-based sampling inference, where the only source of uncertainty is the outcome of the sampling method.