A Comparative Analysis of Drinking Water Quality at Railway Stations in Tripura Using TOPSIS, VIKOR, and a PCA-Based Robust Ranking Method

Abstract

Effective ranking of alternatives in multi-criteria decision making (MCDM) problems is vital across disciplines such as engineering, economics, and the social sciences. This study employs two well-established MCDM techniques—TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) and VIKOR (VlseKriterijumska Optimizacija I Kompromisno Resenje)—to assess the drinking water quality at 27 railway stations in Tripura, India. A total of 13 water quality parameters were initially considered, however Principal Component Analysis (PCA) revealed that only 5 parameters were statistically significant. These 5 key parameters were subsequently used for ranking the railway stations through both TOPSIS and VIKOR methods. To evaluate the consistency between the two ranking methods, Spearman's rank correlation coefficient was calculated and found to be close to zero, indicating a lack of correlation. In response to this discrepancy, a new approach named Robust Ranking Method (RRM) has been proposed here. The RRM integrates the 5 significant parameters using a linear combination, with PCA-derived eigenvalues as weights, to provide a more stable and interpretable ranking of drinking water quality across the stations. The proposed methodology offers a novel and reliable framework for environmental quality assessment in multi-criteria contexts.