Missing data analysis with fuzzy C-Means: A study of its application in a psychological scenario

摘要

In scientific research, and particularly in psychological studies, data for some variables in the database to be analyzed may well be missing. If not dealt with in the correct way, the missing values may weaken or even compromise the validity of research into the database, especially if it is a small one. In this paper we introduce the most common solutions to this problem offered by the most popular statistical software and a technique based on the most famous fuzzy clustering algorithm: Fuzzy C-Means (FCM). Then we compare these methodologies in order to highlight the peculiar characteristics of each solution. The comparison was made in a psychological research environment, using a database of in-patients who have a diagnosis of mental retardation. The results demonstrate that completion techniques, and in particular the one based on FCM, lead to effective data imputation, avoiding the deletion of elements with missing data, which diminishes the power of the research.