Missing data imputation by utilizing information within incomplete   instances

doi:10.1016/j.jss.2010.11.887

CORC > 北京大学 > 信息科学技术学院

	Missing data imputation by utilizing information within incomplete instances
	Zhang, Shichao ; Jin, Zhi ; Zhu, Xiaofeng
刊名	journal of systems and software
	2011
关键词	Incomplete data analysis Missing value Nonparametric imputation Iterative imputation LIKELIHOOD ALGORITHM DATABASES VALUES
DOI	10.1016/j.jss.2010.11.887
英文摘要	This paper proposes to utilize information within incomplete instances (instances with missing values) when estimating missing values. Accordingly, a simple and efficient nonparametric iterative imputation algorithm, called the NIIA method, is designed for iteratively imputing missing target values. The NIIA method imputes each missing value several times until the algorithm converges. In the first iteration, all the complete instances are used to estimate missing values. The information within incomplete instances is utilized since the second imputation iteration. We conduct some experiments for evaluating the efficiency, and demonstrate: (1) the utilization of information within incomplete instances is of benefit to easily capture the distribution of a dataset; and (2) the NIIA method outperforms the existing methods in accuracy, and this advantage is clearly highlighted when datasets have a high missing ratio. (C) 2010 Elsevier Inc. All rights reserved.; Computer Science, Software Engineering; Computer Science, Theory & Methods; SCI(E); EI; 15; ARTICLE; 3; 452-459; 84
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/240589]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Zhang, Shichao,Jin, Zhi,Zhu, Xiaofeng. Missing data imputation by utilizing information within incomplete instances[J]. journal of systems and software,2011.
APA	Zhang, Shichao,Jin, Zhi,&Zhu, Xiaofeng.(2011).Missing data imputation by utilizing information within incomplete instances.journal of systems and software.
MLA	Zhang, Shichao,et al."Missing data imputation by utilizing information within incomplete instances".journal of systems and software (2011).