Description

One of the important problems in data quality is the presence of missing data. So missing data imputation is an important issue in learning from incomplete data. Imputation is a procedure that replaces the missing values in a data set by some plausible values. Various techniques have been developed to deal with missing values in data sets with homogenous attributes. But those approaches are independent of all either continuous or discrete value. We propose a new setting of missing data imputation, i.e., imputing missing data in data sets with heterogeneous attributes, referred to as imputing mixed-attribute data sets. Although many real applications are in this setting, there is no estimator designed for imputing mixed-attribute data sets. In this paper we propose a Nonparametric Iterative Imputation Method based on a Mixture Kernel is used for imputing missing data in data sets with heterogeneous attributes which admits both continuous and discrete data. The proposed iterative imputation method which imputes each missing value several times until the algorithm converges.