Naive Bayes as an Imputation Tool for Classification Problems

Authors:
Antonio J. T. Garcia;Eduardo R. Hruschka
Affiliations:
IBM Software Group, Brazil;Catholic University of Santos (UniSantos), Brazil.
Venue:
HIS '05 Proceedings of the Fifth International Conference on Hybrid Intelligent Systems
Year:
2005

Citing 0
Cited 2

On the influence of imputation in classification: practical issues

Journal of Experimental & Theoretical Artificial Intelligence
An experimental study on the use of nearest neighbor-based imputation algorithms for classification tasks

Data & Knowledge Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

We investigate the use of the Naive Bayes classifier as an imputation tool for classification problems, elaborating on why the usually employed Majority Method may insert biases in a classification context. Considering Rubin麓s typology for the distribution of missingness, we have performed experiments that illustrate how an imputation process may influence classification tasks. Our results show that imputations performed by the Naïve Bayes can be useful for other classifiers (decision trees and nearest neighbors). In this sense, interesting hybrid systems to classify datasets with missing values can be derived.