Chi² Test to Determine the Cut-Off Value for Anomalies Detection with Mahalanobis Distance

Abstract

This work aims to contemplate the detection of possible anomalies in a dynamic, robust, and effective way using Mahalanobis distance readily with the Chi² test. Tests were performed with p-values of a data set and the cut-off value, both generated by the Chi² test, reliably and dynamically detected possible anomalies. Therefore, this anomaly detection method is more effective for regular anomaly determination based on points farthest from the center.