数学科学研究所
Insitute of Mathematical Science

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

Seminar| Institute of Mathematical Sciences

Time:Tuesday, August 17th, 2021, 14:00-15:00 

LocationTencent Meeting

 

Speaker:  Xuerong Chen , Southwestern University of Finance

Abstract: 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.


Tencent Link: https://meeting.tencent.com/s/YJ1XqWNF9tL5

Meeting ID: 575 574 948

Meeting Password: 123456


地址:上海市浦东新区华夏中路393号
邮编:201210
上海市徐汇区岳阳路319号8号楼
200031(岳阳路校区)