Kernel classification rules in the presence of missing values

The nonparametric kernel classification rule derived from incomplete data is studied. Methods of designing kernel decision rules possessing optimal asymptotic properties are proposed. Consistency and rates of convergence are examined. It is argued that the replacement methods using the regression approach can lead to the inconsistency of resulting decision rules. On the other hand, a method employing the concept of predictive density yields asymptotically optimal classification rules.<>