4.5 Article

Nonignorable Missing Data, Single Index Propensity Score and Profile Synthetic Distribution Function

期刊

JOURNAL OF BUSINESS & ECONOMIC STATISTICS
卷 40, 期 2, 页码 705-717

出版社

TAYLOR & FRANCIS INC
DOI: 10.1080/07350015.2020.1860065

关键词

Missing not at random; Nonignorable missing; Pseudo-conditional likelihood; Single index model; Synthetic distribution

资金

  1. National Natural Science Foundation of China (NSFC) [11871402, 11931014]
  2. Fundamental Research Funds for the Central Universities [JBK1806002]

向作者/读者索取更多资源

In this study, we address the challenge of non-random missing data by considering an unspecified single index model for the propensity score and constructing a pseudo-likelihood based on complete data. The pseudo-likelihood provides asymptotically normal estimates and simulations demonstrate its favorable performance compared to existing methods.
In missing data problems, missing not at random is difficult to handle since the response probability or propensity score is confounded with the outcome data model in the likelihood. Existing works often assume the propensity score is known up to a finite dimensional parameter. We relax this assumption and consider an unspecified single index model for the propensity score. A pseudo-likelihood based on the complete data is constructed by profiling out a synthetic distribution function that involves the unknown propensity score. The pseudo-likelihood gives asymptotically normal estimates. Simulations show the method compares favorably with existing methods.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据