Premium
Multiple Augmentation with Partial Missing Regressors
Author(s) -
Ma Shuangge
Publication year - 2006
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.200510168
Subject(s) - missing data , observable , data set , set (abstract data type) , statistics , mathematics , econometrics , computer science , algorithm , data mining , physics , quantum mechanics , programming language
In large cohort studies, it is common that a subset of the regressors may be missing for some study subjects by design or happenstance. In this article, we apply the multiple data augmentation techniques to semiparametric models for epidemiologic data when a subset of the regressors are missing for some subjects, under the assumption that the data are missing at random in the sense of Rubin (2004) and that the missingness probabilities depend jointly on the observable subset of regressors, on a set of observable extraneous variables and on the outcome. Computational algorithms for the Poor Man's and the Asymptotic Normal data augmentations are investigated. Simulation studies show that the data augmentation approach generates satisfactory estimates and is computationally affordable. Under certain simulation scenarios, the proposed approach can achieve asymptotic efficiency similar to the maximum likelihood approach. We apply the proposed technique to the Multi‐Ethic Study of Atherosclerosis (MESA) data and the South Wales Nickel Worker Study data. (© 2006 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)