Constructing support vector machines with missing data

Support vector machine (SVM) classification is a statistical learning method which easily accommodates large numbers of predictors and can discover both linear and nonlinear relationships between the predictors and outcomes. A common challenge is constructing an SVM when the training set includes observations with missing predictor values. In this paper, we identify when missing data can bias an SVM classifier. Because the missing data mechanisms which bias SVMs differ from the traditional framework of missing-at-random and missing-not-at-random, we argue for an SVM-specific framework for understanding missing data. Furthermore, we compare a number of missing data strategies for SVMs in a simulation study and real data example, and we make recommendations for SVM users based on the simulation study.