A novel integrated objective-subjective weighting method using principal component analysis to correct overrepresentation of correlated criteria in sustainability decision-making
Abstract
Indicators can be used as criteria in multicriteria decision-making. However, when indicators measure the same phenomenon, they exhibit correlations that can bias decision-making. Methods that consider correlations have limitations and are either objective or subjective. This paper proposes a new integrated objective-subjective weighting method that accounts for criterion correlations via principal component analysis. This method favours objective weights when criteria are correlated and subjective weights when they are uncorrelated. The method was validated through three comparative case studies and six sensitivity analyses, with a qualitative analysis of decision-relevant rank changes. Results show decision-relevant rank changes across all case studies, highlighting a correlated structure in decision-making in 11 of 13 MCDM models. 10 MCDM models report changes in the countries that constitute the top or bottom 5. 9 MCDM models report that most countries changed ranks, while 8 MCDM models report that countries have moved by more than 5 ranks. The sensitivity analysis highlights the method's contribution: it may enable more balanced decision-making. Pairwise comparisons allow for a more complete configuration that better captures the correlations among the criteria and their weights. The sensitivity analysis also identified limitations, including incomplete consideration of variance and computational complexity. Further research should apply principal component analysis to remove redundant criteria and validate the proposed method's decision quality.
Related
- Integrated Urban Climate Resilience and Sustainability Assessment System for Urban Regeneration and Building Renovation
- Food sustainability and sovereignty in tension: An integrated assessment of nutritional, environmental, and self-sufficiency dimensions in the French food supply
- Integrated experimental and machine learning-driven multi-objective optimization for phenol removal via silica aerogel/ZSM-5 nanocomposite: Isotherm and kinetic analysis, thermodynamic insights and pareto-based process design
- Targeting integrated daylighting comfort in deep office by multi-objective optimization using partial vertical deployment of adaptive corrugated shadings
- Hybrid stacked bidirectional deep learning with attention based air pollution prediction for environmental sustainability
BibTeX
@article{anglehartnunes2026novel,
title = {{A novel integrated objective-subjective weighting method using principal component analysis to correct overrepresentation of correlated criteria in sustainability decision-making}},
author = {Jessy Anglehart-Nunes and Mathias Glaus and Jonathan Villot},
journal = {Environmental and Sustainability Indicators},
year = {2026},
month = oct,
doi = {10.1016/j.indic.2026.101573},
url = {https://hal.science/hal-05820472v1},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - A novel integrated objective-subjective weighting method using principal component analysis to correct overrepresentation of correlated criteria in sustainability decision-making
AU - Jessy Anglehart-Nunes
AU - Mathias Glaus
AU - Jonathan Villot
PY - 2026
DA - 2026/10/20
JO - Environmental and Sustainability Indicators
DO - 10.1016/j.indic.2026.101573
UR - https://hal.science/hal-05820472v1
AB - Indicators can be used as criteria in multicriteria decision-making. However, when indicators measure the same phenomenon, they exhibit correlations that can bias decision-making. Methods that consider correlations have limitations and are either objective or subjective. This paper proposes a new integrated objective-subjective weighting method that accounts for criterion correlations via principal component analysis. This method favours objective weights when criteria are correlated and subjective weights when they are uncorrelated. The method was validated through three comparative case studies and six sensitivity analyses, with a qualitative analysis of decision-relevant rank changes. Results show decision-relevant rank changes across all case studies, highlighting a correlated structure in decision-making in 11 of 13 MCDM models. 10 MCDM models report changes in the countries that constitute the top or bottom 5. 9 MCDM models report that most countries changed ranks, while 8 MCDM models report that countries have moved by more than 5 ranks. The sensitivity analysis highlights the method's contribution: it may enable more balanced decision-making. Pairwise comparisons allow for a more complete configuration that better captures the correlations among the criteria and their weights. The sensitivity analysis also identified limitations, including incomplete consideration of variance and computational complexity. Further research should apply principal component analysis to remove redundant criteria and validate the proposed method's decision quality.
SN - 2665-9727
ER -