Estimation of Missing Data Using Neural Networks and Decision Trees

Estimation of Missing Data Using Neural Networks and Decision Trees

Tshilidzi Marwala (University of Witwatersrand, South Africa)
DOI: 10.4018/978-1-60566-336-4.ch011
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

This chapter introduces a novel paradigm to impute missing data that combines a decision tree, autoassociative neural network (AANN) model and a principal component analysis-neural network (PCA-NN) based model. These models are designed to answer the crucial question of whether the optimization bounds actually matter. For each model, the decision tree is used to predict search bounds for a hybrid simulated annealing and genetic algorithm method that minimizes an error function derived from the respective model. The models’ ability to impute missing data is tested and then compared using HIV sero-prevalance data. Results indicate an average increase in accuracy of 13% with the AANN based model’s average accuracy increasing from 75.8% to 86.3% while that of the PCA-NN based model increasing from 66.1% to 81.6%.

Complete Chapter List

Search this Book:
Reset