An Interactive and Understandable Method to Treat Missing Values: Application to a Medical Data Set

摘要

Many analysis tasks have to deal with missing values and some of them have developed specific and internal treatments to guess them. In this paper we present the use of a new method, called MVC (Missing Values Completion), for this question: MVC is based on data preprocessing which gives prominence to understandable associations and gives the user a central part. Such qualities will allow to use it for the data cleaning step of the Knowledge Discovery in Databases process. The efficiency of this method rests on the Robust Association Rules algorithm that we have proposed. This algorithm extends the concept of association rules for databases with multiple missing values. We give some examples of the use of MVC in a real world data set (in medicine), highlighting typical use of this method.