Title: An alternative sensitive analysis approach for missing not at random
Authors: Chiu-Hsieh Hsu - University of Arizona (United States) [presenting]
Chengcheng Hu - University of Arizona (United States)
Yulei He - CDC (United States)
Abstract: Missing mechanism is unverifiable. Often researchers perform sensitivity analysis to evaluate the impact of various missing mechanisms. All the existing sensitivity analysis approaches for missing not at random (MNAR) require to fully specify the relationship between the missing value and the missing probability. The relationship is specified using a selection model, a pattern-mixture model or a shared parameter model. We propose an alternative sensitive analysis approach for MNAR using a nonparametric multiple imputation approach. The proposed approach only requires to specify the correlation between the missing value and the missing probability. The correlation is a standardized measured and can be directly used to indicate the magnitude of MNAR. Numerical results indicate the proposed approach performs well and can be used as an alternative approach for MNAR.