A Nonresponse Bias Correction using Nonrandom Followup with an Application to the Gender Entrepreneurship Gap
We develop a nonresponse correction applicable to any setting in which multiple attempts to contact subjects affect whether researchers observe variables without affecting the variables themselves. Our procedure produces point estimates of population averages using selected samples without requiring randomized incentives or assuming selection bias cancels out for any within-respondent comparisons. Applying our correction to a 16% response rate survey of University of Wisconsin-Madison undergraduates, we estimate a 15 percentage point male-female entrepreneurial intention gap. Our estimates attribute the 20 percentage point uncorrected within-respondent gap to positive bias for men and negative bias for women, highlighting the value of within-group nonresponse corrections.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeSelection biasSurveySimilar Papers 제목 키워드 기반
A Longitudinal Framework for Predicting Nonresponse in Panel Surveys
Nonresponse in panel studies can lead to a substantial loss in data quality due to its potential to introduce bias and distort survey estimates. Recent work investigates the usage of machine learning to predict nonrespon…
BIG-bench Machine LearningGenerating Followup Questions for Interpretable Multi-hop Question Answering
We propose a framework for answering open domain multi-hop questions in which partial information is read and used to generate followup questions, to finally be answered by a pretrained single-hop answer extractor. This …
Multi-hop Question AnsweringQuestion AnsweringQuestion GenerationQuestion-Generation+2Recovering Loss to Followup Information Using Denoising Autoencoders
Loss to followup is a significant issue in healthcare and has serious consequences for a study's validity and cost. Methods available at present for recovering loss to followup information are restricted by their express…
DenoisingTesting for Restricted Stochastic Dominance under Survey Nonresponse with Panel Data: Theory and an Evaluation of Poverty in Australia
This paper lays the groundwork for a unifying approach to stochastic dominance testing under survey nonresponse that integrates the partial identification approach to incomplete data and design-based inference for comple…
SurveyFOLLOWUPQG: Towards Information-Seeking Follow-up Question Generation
Humans ask follow-up questions driven by curiosity, which reflects a creative human cognitive process. We introduce the task of real-world information-seeking follow-up question generation (FQG), which aims to generate f…
InformativenessQuestion GenerationQuestion-Generation