Premium
A toolkit in SAS for the evaluation of multiple imputation methods
Author(s) -
Brand Jaap P.L.,
Buuren Stef,
GroothuisOudshoorn Karin,
Gelsema Edzard S.
Publication year - 2003
Publication title -
statistica neerlandica
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.52
H-Index - 39
eISSN - 1467-9574
pISSN - 0039-0402
DOI - 10.1111/1467-9574.00219
Subject(s) - imputation (statistics) , polytomous rasch model , categorical variable , computer science , missing data , data mining , software , regression , statistics , machine learning , mathematics , item response theory , programming language , psychometrics
This paper outlines a strategy to validate multiple imputation methods. Rubin's criteria for proper multiple imputation are the point of departure. We describe a simulation method that yields insight into various aspects of bias and efficiency of the imputation process. We propose a new method for creating incomplete data under a general Missing At Random (MAR) mechanism. Software implementing the validation strategy is available as a SAS/IML module. The method is applied to investigate the behavior of polytomous regression imputation for categorical data.