NONPARAMETRIC SURVEY RESPONSE ERRORS*
提出非参数方法识别和估计调查响应中的偏差，分析受访者特征和调查设计如何影响响应误差，并利用估计结果纠正偏差，同时为改进调查设计提供指导。
I present nonparametric methods to identify and estimate the biases associated with response errors. When applied to survey data, these methods can be used to analyze how observable and unobservable characteristics of the respondent, and characteristics of the design of the survey, affect errors in the responses. This provides a method to correct the biases that those errors generate, by using the estimated response errors to “undo” those biases. The results are useful also to design better surveys, since they point at characteristics of the design and of subpopulations of respondents that can provide identification of response errors. Several models are considered.