Using Binary Paradata to Correct for Measurement Error in Survey Data Analysis
Using Binary Paradata to Correct for Measurement Error in Survey Data Analysis
复制标题
DOI：
10.1080/01621459.2015.1130632
复制
发表时间：
2016-04
影响因子：
3.7
通讯作者：
D. N. Da Silva;C. Skinner;Jae Kwang Kim
中科院分区：
文献类型：
--
作者：
D. N. Da Silva;C. Skinner;Jae Kwang Kim
这里的数据是指单位一级关于观测到的辅助变量的数据，通常不具有直接的科学意义，但可能提供有关该单位调查数据质量的信息。调查研究人员对如何使用这些数据越来越感兴趣。到目前为止，它用于减少无响应的偏倚比用于校正测量误差更受关注。本文认为后者的重点是二进制参数表示测量误差的存在。一个激励性的应用程序涉及回归模型的推断，其中收入是一个测量误差的协变量，而受访者是否提到工资记录是一个paradox变量。我们指定一个参数模型，允许正态分布或t分布测量误差，并讨论确定回归系数所需的假设。我们提出了两种估计方法，考虑到复杂的调查设计：伪最大似然估计和参数分数插补。这些方法进行了评估，在模拟研究，并适用于回归的剥夺的收入和其他协变量，使用英国家庭小组调查数据的措施。结果发现，所提出的方法来校正测量误差减少了偏差，并提高了基于精确观测的简单方法的精度。我们简要概述了可能的扩展使用这种方法在调查过程的早期阶段。补充材料可在线获取。
ABSTRACT Paradata refers here to data at unit level on an observed auxiliary variable, not usually of direct scientific interest, which may be informative about the quality of the survey data for the unit. There is increasing interest among survey researchers in how to use such data. Its use to reduce bias from nonresponse has received more attention so far than its use to correct for measurement error. This article considers the latter with a focus on binary paradata indicating the presence of measurement error. A motivating application concerns inference about a regression model, where earnings is a covariate measured with error and whether a respondent refers to pay records is the paradata variable. We specify a parametric model allowing for either normally or t-distributed measurement errors and discuss the assumptions required to identify the regression coefficients. We propose two estimation approaches that take account of complex survey designs: pseudo-maximum likelihood estimation and parametric fractional imputation. These approaches are assessed in a simulation study and are applied to a regression of a measure of deprivation given earnings and other covariates using British Household Panel Survey data. It is found that the proposed approach to correcting for measurement error reduces bias and improves on the precision of a simple approach based on accurate observations. We outline briefly possible extensions to uses of this approach at earlier stages in the survey process. Supplemental materials are available online.