A comparative study of missing value estimation methods: which method performs better?

Link to publisher's homepage at http://ieeexplore.ieee.org

Saved in:

Bibliographic Details
Main Authors:	Eng Aik, Lim, Zarita, Zainuddin
Other Authors:	ealim@unimap.edu.my
Format:	Working Paper
Language:	English
Published:	Institute of Electrical and Electronics Engineering (IEEE) 2009
Subjects:	Missing data Radial basis function networks Estimation theory Bayes methods Least squares approximations Air pollutant data Missing value estimation
Online Access:	http://dspace.unimap.edu.my/xmlui/handle/123456789/7393
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Universiti Malaysia Perlis
Language:	English

id	my.unimap-7393
record_format	dspace
spelling	my.unimap-73932009-12-10T03:39:51Z A comparative study of missing value estimation methods: which method performs better? Eng Aik, Lim Zarita, Zainuddin ealim@unimap.edu.my Missing data Radial basis function networks Estimation theory Bayes methods Least squares approximations Air pollutant data Missing value estimation Link to publisher's homepage at http://ieeexplore.ieee.org Missing data is a problem that permeates much of the research bring done today. Some data frequently contain missing values such as gene expression data, which most of its down stream analyses for microarray experiments require complete data. In the literature many methods have been proposed to estimate missing values via information of the correlation patterns within the data matrix. In this report we describe an evaluation of top three current methods including a neural network method and two imputation methods on multiple types of data including microarray data, time series data such as air pollutant data and phytoplankton data. Based on the overall performance of the method, we then determine the most appropriate method that can be applied to various data sets. We found that the optimal method (Local Least Square Imputation (LLS) and Bayesian Principle Component Analyses (BPCA)) are all highly competitive to each other in overall results. We tested with Radial Basis Function (RBF) network method which is one of the neural network methods and found that, the overall performance of RBF network is lower than BPCA method and LLS method. According to the overall NRMSE of the three methods, the BPCA method provides the most accurate estimation for missing values. 2009-12-10T03:39:51Z 2009-12-10T03:39:51Z 2008-12-01 Working Paper p.1-5 978-1-4244-2315-6 http://ieeexplore.ieee.org/search/wrapper.jsp?arnumber=4786656 http://hdl.handle.net/123456789/7393 en Proceedings of the International Conference on Electronic Design (ICED 2008) Institute of Electrical and Electronics Engineering (IEEE)
institution	Universiti Malaysia Perlis
building	UniMAP Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaysia Perlis
content_source	UniMAP Library Digital Repository
url_provider	http://dspace.unimap.edu.my/
language	English
topic	Missing data Radial basis function networks Estimation theory Bayes methods Least squares approximations Air pollutant data Missing value estimation
spellingShingle	Missing data Radial basis function networks Estimation theory Bayes methods Least squares approximations Air pollutant data Missing value estimation Eng Aik, Lim Zarita, Zainuddin A comparative study of missing value estimation methods: which method performs better?
description	Link to publisher's homepage at http://ieeexplore.ieee.org
author2	ealim@unimap.edu.my
author_facet	ealim@unimap.edu.my Eng Aik, Lim Zarita, Zainuddin
format	Working Paper
author	Eng Aik, Lim Zarita, Zainuddin
author_sort	Eng Aik, Lim
title	A comparative study of missing value estimation methods: which method performs better?
title_short	A comparative study of missing value estimation methods: which method performs better?
title_full	A comparative study of missing value estimation methods: which method performs better?
title_fullStr	A comparative study of missing value estimation methods: which method performs better?
title_full_unstemmed	A comparative study of missing value estimation methods: which method performs better?
title_sort	comparative study of missing value estimation methods: which method performs better?
publisher	Institute of Electrical and Electronics Engineering (IEEE)
publishDate	2009
url	http://dspace.unimap.edu.my/xmlui/handle/123456789/7393
_version_	1643788802339110912

A comparative study of missing value estimation methods: which method performs better?

Similar Items