Comparisons of K-Mean and K-Medoid General Regression Neural Network for Handling Missing Data

• Activity Number: 444
• Type: Contributed
• Date/Time: Tuesday, August 6, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Janaka Suranga Peragaswaththe Liyanage*+ and Ferry Butar Butar
• Companies: Sam Houston State University and SHSU
• Keywords: Neural Network ; GRNN ; K-Mean ; K-Medoid ; K-Mean ; Ordered Alternative

Abstract

Missing data has struggled researches for many decades. Statisticians have put enormous effort to develop statistical technics to overcome this issue. A perfect method has not been developed yet. Technological advancements in previous decades have revolutionized the way statisticians handle the missing data. Adapting neural networks, one of such technological advancement to handle missing data has provided some better results than the classical statistical techniques. Many studies have carried out to investigate the performance of neural networks when handling missing data. This study aims to compare the outcome of K-Mean and K-Medoid General Neural Network methods in handling missing data.