1 An Empirical Comparison of Techniques for Handling Incomplete Data Using Decision Trees

OBJECTIVE: Increasing the awareness of how incomplete data affects learning and classification accuracy has led to increasing numbers of missing data techniques. This paper investigates the robustness and accuracy of seven popular techniques for tolerating incomplete training and test data for different patters of missing data; different proportions and mechanisms of missing data on resulting tree-based models. METHOD: The seven missing data techniques were compared by artificially simulating different proportions, patterns, and mechanisms of missing data using twenty one complete (i.e. with no missing values) datasets obtained from the UCI repository of machine learning databases [Blake and Merz, 1998]. A 4-way repeated measures design was employed to analyze the data. RESULTS: The simulation results suggest important differences. All methods have their strengths and weaknesses. However, listwise deletion is substantially inferior to the other six techniques while multiple imputation, which utilizes the Expectation Maximization algorithm, represents a superior approach to handling incomplete data. Decision tree single imputation and surrogate variables splitting are more severely impacted by missing values distribute