Higher Order Kernel Function Algorithm for Imputing Missing Values

Ganga. A.R, B. Lakshmipathi

Abstract


Many types of experimental data are with missing values that may occur for a variety of reasons. Most of the data analyses such as classification methods, clustering methods and dimension reduction procedures require complete data. Hence researchers must either remove missing data or preferably estimate the missing values before such procedures are applied. Missing data imputation is a key issue in learning from incomplete data. Various techniques have been developed to deal with missing values in data sets with homogenous attributes. But those approaches are independent of either continuous or discrete values. Recently a new proposal came for setting of missing data imputation with heterogeneous attributes thus by contributing for both continuous and discrete data. This study proposes a higher order spherical kernel based iterative estimator to impute mixed-attribute data sets. Spherical kernel based estimator will give better results than other estimators.


Keywords: Imputation, Data Mining, Kernel methods, Mixed Attribute


Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v3i3.1117

Refbacks

  • There are currently no refbacks.




Copyright (c) 2016 International Journal of Advanced Research in Computer Science