COMPARING ALTERNATIVES FOR ESTIMATION FROM NONPROBABILITY SAMPLES
COMPARING ALTERNATIVES FOR ESTIMATION FROM NONPROBABILITY SAMPLES
复制标题
DOI：
10.1093/jssam/smz003
复制
发表时间：
2020-04-01
影响因子：
2.1
通讯作者：
Valliant, Richard
中科院分区：
文献类型：
--
作者：
Valliant, Richard
非概率样本估计的三种方法是拟随机化、超总体建模和双稳健估计。在第一种情况下，样本被视为通过概率机制获得，但与概率抽样不同，该机制是未知的。在样本中的伪选择概率是通过使用样本结合覆盖所需人群的一些外部数据集来估计的。在超总体方法中，分析变量的观测值被视为由某种模型生成的。该模型根据样本进行估计，并沿着外部总体控制数据，用于将样本投影到总体。具体的技术与通常用于从概率样本进行估计的技术相同或相似，包括二元回归、回归树和校准。当拟随机化和超总体建模相结合时，这被称为双重稳健估计。本文回顾了一些估计选项，并在一系列模拟研究中对它们进行了比较。
Three approaches to estimation from nonprobability samples are quasi-randomization, superpopulation modeling, and doubly robust estimation. In the first, the sample is treated as if it were obtained via a probability mechanism, but unlike in probability sampling, that mechanism is unknown. Pseudo selection probabilities of being in the sample are estimated by using the sample in combination with some external data set that covers the desired population. In the superpopulation approach, observed values of analysis variables are treated as if they had been generated by some model. The model is estimated from the sample and, along with external population control data, is used to project the sample to the population. The specific techniques are the same or similar to ones commonly employed for estimation from probability samples and include binary regression, regression trees, and calibration. When quasi-randomization and superpopulation modeling are combined, this is referred to as doubly robust estimation. This article reviews some of the estimation options and compares them in a series of simulation studies.