1193. On Benefit-of-the-Doubt and weighted arithmetic average composite indicators: Benchmarking and direction-specific improvement paths
Invited abstract in session TB-8: MCDA and Composite Indicators: Issues, advances and applications, stream Multiple Criteria Decision Aiding.
Tuesday, 10:30-12:00Room: Clarendon SR 2.08
Authors (first author is the speaker)
| 1. | Panagiotis Ravanos
|
| Directorate S: Innovation in Science and Policymaking, Unit S3: Science for Modelling, Monitoring and Evaluation, European Commission, Joint Research Center | |
| 2. | Giulio Caperna
|
| Competence Centre on Composite Indicators and Scoreboards, Joint Research Centre of the European Commission | |
| 3. | Giannis Karagiannis
|
| Economics, University of Macedonia |
Abstract
In this paper, we examine the relation between two alternative approaches that are used for aggregating a set of normalized indicators into a composite indicator, namely the weighted arithmetic average and the Benefit-of-the-Doubt (BoD) model. We show that the two approaches differ in terms of two modelling choices: the evaluation benchmark and the aggregation weights, which together determine the best-practice boundary against which entities are evaluated. We verify that the weighted arithmetic average composite indicator can be obtained by means of a directional distance function BoD model regardless of the chosen direction. We demonstrate the usefulness of this result for policy purposes, namely that it enables the identification of optimal improvement paths and targets for individual indicators required for an entity to achieve a particular score for the weighted average composite indicator based on an improvement direction of its choice. We also show how, for radial improvement choices, the overall difference between the BoD and the weighted arithmetic average composite indicator decomposes multiplicatively into a benchmark change and a weighting change component. We illustrate our findings using data from the European Commission’s Cultural and Creative Cities Monitor.
Keywords
- Data Envelopment Analysis
- Multi-Objective Decision Making
Status: accepted
Back to the list of papers