An analysis of four missing data treatment methods for supervised learning

By Gustavo E. A. P. A. Batista, Maria Carolina Monard. 2003

921 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Missing Data Imputation for Supervised Learning (2016, methodology): “Batista and Monard (2003) use this procedure and ﬁnd k -NN imputation can outperform internal methods used by decision trees to treat missing data and summary statistic imputation.”
Local Causal and Markov Blanket Induction for Causal Discovery and Feature Selection for Classification Part I: Algorithms and Empirical Evaluation (2010, methodology): “Techniques #1 and #2 were introduced in Chow and Liu (1968) for learning tree-like graphs and Naı̈ve-Bayes graphs (Duda and Hart, 1973), while modern versions are exemplified in (i) TAN/BAN classifiers that relax the Naı̈ve-Bayes structure (Cheng and Greiner, 2001, 1999; Friedman et al.”
Impact of imputation of missing values on classification error for discrete data (2008, background): “Batista and Monard [16] tested the classification accuracy of two popular classifiers, i.e., C4.5 decision tree [17] and CN2 rule induction algorithm [18], and three imputation methods, namely, mean, mode, and KNN.”
Class Noise vs. Attribute Noise: A Quantitative Study (2003, background): “…et al. 1995, 1996; Redman 1996, 1998; Maletic 2000) and noise handling (Little and Rubin 1987; John 1995; Zhao 1995; Brodley and Friedl 1999; Gamberger et al. 1999, 2000; Teng 1999; Allison 2002; Batista and Monard 2003; Kubica and Moore 2003; Zhu et al. 2003a, 2004) to enhance the data quality.”
Data preparation for data mining (2003, background): “Batista and Monard (2003) propose a new approach to deal with missing values.”
Mining incomplete survey data through classification (2010, background): “In general, a meaningful treatment of missing data shall be relevant to the problem being investigated [4].”
A survey on missing data in machine learning (2021, methodology): “In another study by Batista and Monard [75], the KNN algorithm was experimented to evaluate its efficiency as an imputation method to treat missing data and compared its performance to other algorithms such as by the C4.5 and CN2 and the mean or mode imputation method.”
Types of Machine Learning Algorithms (2010, background): “Depending on the circumstances, researchers have a number of methods to choose from to handle missing data (Batista, 2003).”
Supervised Machine Learning: A Review of Classification Techniques (2007, neutral): “Depending on the circumstances, researchers have a number of methods to choose from to handle missing data (Batista & Monard, 2003).”
KEEL: a software tool to assess evolutionary algorithms for data mining problems (2008, background): “2004), instance selection (Wilson and Martinez 2000) and missing values imputation (Batista and Monard 2003).”
Handling Missing Values when Applying Classification Models (2007, background): “Empirical work on handling missing values has primarily addressed the challenge of induction from incomplete training data (e.g., Rubin, 1987; Dempster et al., 1977; Schafer, 1997; Batista and Monard, 2003; Feelders, 1999; Ghahramani and Jordan, 1994, 1997).”
Machine learning: a review of classification and combining techniques (2006, background): “” Depending on the circumstances, researchers have a number of methods to choose from to handle missing data (Batista and Monard 2003):”