Conditional moment models with data missing at random

• 成果类型: Article
• 署名作者: Hristache, M.; Patilea, V.
• 署名单位: Ecole Nationale de la Statistique et de l'Analyse de l'Information (ENSAI)
• 刊物名称: BIOMETRIKA
• ISSN/ISSBN: 0006-3444
• DOI: 10.1093/biomet/asx025
• 发表日期: 2017
• 页码: 735742
• 关键词: partially linear-models; single-index model; semiparametric regression; EFFICIENCY; responses; restrictions; functionals

摘要

We consider a general statistical model defined by moment restrictions when data are missing at random. Using inverse probability weighting, we show that such a model is equivalent to a model for the observed variables only, augmented by a moment condition defined by the missingness mechanism. Our framework covers parametric and semiparametric mean regressions and quantile regressions. We allow for missing responses, missing covariates and any combination of them. The equivalence result sheds new light on various aspects of missing data, and provides guidelines for building efficient estimators.