Doubly robust multiple imputation using kernel-based techniques

• Type of Material: Article
• Authors: Chiu-Hsieh Hsu, University of Arizona; Yulei He, National Center for Health Statistics, CDC; Yisheng Li, The University of Texas MD Anderson Cancer Center; Qi Long, Emory University; Randall Friese, University of Arizona
• Language: English
• Date: 2016-05-02
• Publisher: Wiley-Blackwell
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2015 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim. "This is the peer reviewed version of the following article, which has been published in final form at. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving."
• Final Published Version (URL): http://dx.doi.org/10.1002/bimj.201400256
• Title of Journal or Parent Work: Biometrical Journal
• Volume: 58
• Issue: 3
• Start Page: 588
• End Page: 606
• Grant/Funding Information: Dr. Qi Long’s work was supported in part by a PCORI award (ME-1303-5840) and an NIH/NINDS grant (R21NS091630).; Dr. Yisheng Li’s research was partially supported by the National Cancer Institute grant P30 CA016672.; Dr. Chiu-Hsieh Hsu’s research was partially supported by the National Cancer Institute grant P30 CA 23704.
• Keywords: VALUES; Physical Sciences; Local imputation; Bootstrap; MISSING DATA; Bandwidth; Statistics & Probability; Mathematical & Computational Biology; Model misspecification; REPEATED OUTCOMES; Nonparametric; Life Sciences & Biomedicine; SEMIPARAMETRIC REGRESSION; Science & Technology; MODELS; NONRESPONSE; Mathematics
• Research Categories: Health Sciences, Public Health; Health Sciences, Epidemiology

Abstract

We consider the problem of estimating the marginal mean of an incompletely observed variable and develop a multiple imputation approach. Using fully observed predictors, we first establish two working models: one predicts the missing outcome variable, and the other predicts the probability of missingness. The predictive scores from the two models are used to measure the similarity between the incomplete and observed cases. Based on the predictive scores, we construct a set of kernel weights for the observed cases, with higher weights indicating more similarity. Missing data are imputed by sampling from the observed cases with probability proportional to their kernel weights. The proposed approach can produce reasonable estimates for the marginal mean and has a double robustness property, provided that one of the two working models is correctly specified. It also shows some robustness against misspecification of both models. We demonstrate these patterns in a simulation study. In a real-data example, we analyze the total helicopter response time from injury in the Arizona emergency medical service data.