EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Decomposing DEA self-efficiency: A cross-efficiency-based quantity–price framework

Yanjun Liu, Zanfu Ma iD, Hao Zhan

PLOS One · 10.08.2026 · 21 (8) · e0355649

DOI: 10.1371/journal.pone.0355649 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 10.08.2026. Verfasst von Yanjun Liu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Transport and Logistics, Guangzhou Railway Polytechnic, Guangzhou, China. Hauptthemen laut MEDLINE: Models, Economic, Commerce. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Provincial Higher Education Institutions Key Field Special Fund, Humanities and Social Science Fund of Ministry of Education of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data Envelopment Analysis (DEA) self-efficiency scores are widely used for measuring relative performance. Although it has long been recognized that DEA efficiency depends on endogenous weight systems and the underlying production technology, the mechanisms through which these factors jointly contribute to observed efficiency differences remain insufficiently understood and difficult to quantify. Existing cross-efficiency studies have primarily focused on peer-appraisal aggregation and ranking performance, while the informational structure embedded in cross-efficiency matrices has received comparatively little attention. This study exploits the dual informational organization of cross-efficiency matrices to develop a quantity–price decomposition framework for DEA self-efficiency. Row-wise comparisons preserve common valuation systems and predominantly reflect production-position information, whereas column-wise comparisons preserve common quantity bundles and predominantly reflect endogenous valuation information generated by alternative shadow-price systems. Based on four cross-efficiency elements, a reciprocal Quantity Index (QI) and a reciprocal Price Index (PI) are constructed to decompose pairwise self-efficiency differences into quantity-related and valuation-related components. The proposed decomposition provides an exact algebraic representation of self-efficiency differences, while its interpretation should be understood as a dominant-information decomposition within the DEA framework because every cross-efficiency element is jointly determined by observed quantities and endogenous shadow prices. Theoretical properties of the proposed framework are established, including positivity, reciprocity, spectral equivalence, and the existence and uniqueness of principal eigenvectors. An empirical illustration using data from Chinese cities demonstrates how production-position information and endogenous valuation information can be extracted from cross-efficiency matrices and how alternative technological assumptions simultaneously reshape quantity and valuation structures. Rather than proposing a new cross-efficiency evaluation method, this study provides an interpretive framework for quantifying how endogenous weighting systems and technological assumptions contribute to DEA self-efficiency formation. By shifting attention from peer-appraisal aggregation to the informational structure underlying DEA self-efficiency, the study offers an additional perspective for understanding model dependence, scale efficiency, and the formation mechanism of DEA self-efficiency.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Models, EconomicCommerceAlgorithms

Autor:innen und Institutionen

  • School of Transport and Logistics, Guangzhou Railway Polytechnic, Guangzhou, China.
  • School of Economics and Management, Wenzhou University of Technology, Wenzhou, China.

ORCID-Profile: Zanfu Ma

Förderung

  • Guangdong Provincial Higher Education Institutions Key Field Special Fund
  • Humanities and Social Science Fund of Ministry of Education of China

Zitieren

APA

Liu, Y., Ma, Z., & Zhan, H. (2026). Decomposing DEA self-efficiency: A cross-efficiency-based quantity–price framework. PLOS One, 21(8), e0355649. https://doi.org/10.1371/journal.pone.0355649

Vancouver

Liu Y, Ma Z, Zhan H. Decomposing DEA self-efficiency: A cross-efficiency-based quantity–price framework. PLOS One. 2026;21(8):e0355649. doi:10.1371/journal.pone.0355649

BibTeX
@article{Liu2026,
  author = {Liu, Yanjun and Ma, Zanfu and Zhan, Hao},
  title = {Decomposing DEA self-efficiency: A cross-efficiency-based quantity–price framework},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {8},
  pages = {e0355649},
  doi = {10.1371/journal.pone.0355649}
}
Kostenlos starten →