The choice of an electroencephalogram (EEG) reference has fundamental importance and could be critical during clinical decision-making because an impure EEG reference could falsify the clinical measurements and subsequent inferences. In this research, the suitability of three EEG references was compared while classifying depressed and healthy brains using a machine-learning (ML)-based validation method. In this research, the EEG data of 30 unipolar depressed subjects and 30 age-matched healthy controls were recorded. The EEG data were analyzed in three different EEG references, the link-ear reference (LE), average reference (AR), and reference electrode standardization technique (REST). The EEG-based functional connectivity (FC) was computed. Also, the graph-based measures, such as the distances between nodes, minimum spanning tree, and maximum flow between the nodes for each channel pair, were calculated. An ML scheme provided a mechanism to compare the performances of the extracted features that involved a general framework such as the feature extraction (graph-based theoretic measures), feature selection, classification, and validation. For comparison purposes, the performance metrics such as the classification accuracies, sensitivities, specificities, and F scores were computed. When comparing the three references, the diagnostic accuracy showed better performances during the REST, while the LE and AR showed less discrimination between the two groups. Based on the results, it can be concluded that the choice of appropriate reference is critical during the clinical scenario. The REST reference is recommended for future applications of EEG-based diagnosis of mental illnesses. © 2018, Springer Science+Business Media, LLC, part of Springer Nature.