A COMBINED EWM AND MULTIVARIATE STATISTICAL APPROACH FOR EVALUATING GREEN FINANCE AND ECONOMIC SUSTAINABILITY
Keywords:
Multivariate statistical analysis, Entropy weight method, Spatial clustering, Canonical correlation analysis, Eco-sustainability evaluationAbstract
Unraveling the nexus between financial allocation and ecological performance demands a framework capable of dismantling complex spatial heterogeneities. This study constructs a multidimensional statistical pipeline analyzing cross-sectional data across thirty Chinese provinces. Following objective dimension reduction via the entropy weight method, spatial clustering strictly partitions the landscape into distinct developmental tiers. Canonical correlation analysis subsequently extracts orthogonal structural equations, yielding a systemic coupling coefficient of 0.976. The derived loadings explicitly quantify a dual-edged transition mechanism: ecological sustainability relies heavily on capital friction against high-energy sectors (loading: -0.869), running parallel to targeted capitalization that accelerates industrial emission reductions (loading: 0.784). Beyond immediate operational insights, this research provides a mathematically rigorous blueprint for macroeconomic restructuring. By mapping these exact directional constraints, the framework equips policymakers to abandon homogeneous interventions, facilitating precision green resource allocation across highly polarized regional economies.References
[1] Li B, Wang X, Khurshid A, et al. Environmental governance, green finance, and mitigation technologies: pathways to carbon neutrality in European industrial economies. International Journal of Environmental Science and Technology, 2025, 22(15): 14899-14912.
[2] Lv C, Bian B, Lee C, et al. Regional gap and the trend of green finance development in China. Energy Economics, 2021, 102: 105476.
[3] Wang Z, Wang F, Ma S. Research on the coupled and coordinated relationship between ecological environment and economic development in China and its evolution in time and space. Polish Journal of Environmental Studies, 2025, 34(3): 3333-3342.
[4] Huang H, Gao H, Han J. A macroeconomic data fusion method based on machine learning. Statistical Research, 2022, 39(5): 134-145.
[5] Chen B, Wang F. Macroeconomic indicators, technical indicators and treasury bond futures price forecasting: an empirical test based on random forest machine learning. Statistics & Information Forum, 2019, 34(6): 29-35.
[6] Luo J, Zhuo W, Liu S, et al. The optimization of carbon emission prediction in low carbon energy economy under big data. IEEE Access, 2024, 12: 14690-14702.
[7] Meng T, Yao C. Statistical evaluation of the coupled and coordinated development of digital finance and high-quality real economy. Statistics & Decision, 2024(8).
[8] Zhang H, Deng H. Photovoltaic evaluation in buildings integrally based on entropy weight and grey relational analysis. 2025 8th International Conference on Power and Energy Applications (ICPEA). 2025: 526-531.
[9] Ji Q, Sun Y, Hu Y, et al. A survey of deep clustering algorithms. Journal of Beijing University of Technology, 2021, 47(8): 912-924.
[10] Wei Y, Wang B, Ma L. Statistical evaluation of China's digital economy development level. Statistics & Decision, 2024(10).