An Integrated Approach for Screening Multidimensional Indicators in Combat Capability Assessment
Open Access
- 1 January 2025
- journal article
- Published by Wiley in Journal of Mathematics
- Vol. 2025 (1)
Abstract
Addressing the unique challenges of multidimensional correlations, multicollinearity, data scarcity, and irregularity in combat capability assessment, this study proposes a tailored integrated qualitative–quantitative approach for efficient indicator screening. Unlike standalone or generic applications of dimensionality reduction techniques, the approach intentionally combines principal component analysis (PCA), factor analysis (FA), and gray relational analysis (GRA) to align with the specific demands of combat contexts. PCA first reduces dimensionality by transforming correlated variables into orthogonal principal components, mitigating multicollinearity while retaining key variance; FA then refines this reduced set by extracting interpretable latent factors and clarifying their practical meaning via rotation, ensuring alignment with real‐world operational scenarios; finally, GRA—selected for its robustness to small/irregular datasets—is introduced as an auxiliary tool to validate and optimize the indicator set. Compared to traditional or generic statistical methods, this integration achieves three key improvements: (1) it simultaneously resolves multicollinearity and data scarcity, two long‐standing dilemmas unique to combat capability assessments; (2) it balances statistical rigor with operational interpretability; and (3) it reduces indicator sets by 54% while retaining over 80% of critical combat‐related information, significantly enhancing assessment efficiency.Keywords
Funding Information
- National Natural Science Foundation of China (72071209)
This publication has 29 references indexed in Scilit:
- Feasible model-based principal component analysis: Joint estimation of rank and error covariance matrixComputational Statistics & Data Analysis, 2024
- Research on the construction of weaponry indicator system and intelligent evaluation methodsScientific Reports, 2023
- Multiobjective optimization to assess dengue control costs using a climate-dependent epidemiological modelScientific Reports, 2023
- Multi-view clustering indicator learning with scaled similarityPattern Analysis and Applications, 2023
- Evaluation method and optimization strategies of resilience for air & space defense system of systems based on kill network theory and improved self-information quantityDefence Technology, 2023
- Evaluating Internet hospitals by a linguistic Z-number-based gained and lost dominance score method considering different risk preferences of expertsInformation Sciences, 2023
- Feature screening under missing indicator imputation with non-ignorable missing responseComputational Statistics & Data Analysis, 2020
- A multi-objective perspective on performance assessment and automated selection of single-objective optimization algorithmsApplied Soft Computing, 2020
- A data-driven health indicator extraction method for aircraft air conditioning system health monitoringChinese Journal of Aeronautics, 2019
- A hybrid approach using two-level DEA for financial failure prediction and integrated SE-DEA and GCA for indicators selectionApplied Mathematics and Computation, 2015