EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

98. A cross-efficiency DEA approach for composite indicators: Revisiting Environmental Performance Index

Invited abstract in session TB-48: DEA applications in Environment and Sustainability I, stream Data Envelopment Analysis and its Application.

Tuesday, 10:30-12:00
Room: 60 (building: 324)

Authors (first author is the speaker)

1. Saransh Tiwari
Decision Sciences, Indian Institute of Management (IIM) Lucknow
2. Sanjeet Singh
Decision Sciences, Indian Institute of Management Lucknow
3. Utsav Pandey
Decision Sciences, Indian Institute of Management Lucknow

Abstract

To promote and encourage sustainable development in favour of ensuring an egalitarian and environmentally secure future, Yale and Columbia Universities jointly with World Economic Forum developed the Environmental Performance Index (EPI). The EPI is a composite index of environmental and sustainability indicators that quantifies and assesses a country’s environmental performance based on three broad policy objectives: climate change, environmental health, and ecosystem vitality. This paper proposes an approach based on the cross-efficiency data envelopment analysis (DEA) for estimating the EPI. We propose cross-efficiency models for settings where there are only outputs (without inputs), as in composite indicator construction, that provides unique cross-efficiency scores. As cross-efficiency incorporates both self- and peer-evaluation, it offers a more acceptable and reasonable mechanism for computing the EPI. Utilizing the scores obtained via the cross-efficiency DEA approach, we extend our analysis by employing the regression to determine the relative importance and contribution of the variables used in EPI construction and find suitable weights that could be assigned to the indicators if the decision-maker desires to estimate the countries’ EPI scores via fixed weights. The limitations of the existing methodology for EPI estimation, which is based on a non-optimization approach with weights assigned to the indicators subjectively, are overcome in our proposed approach.

Keywords

Status: accepted

Back to the list of papers