Decomposition of the Interval Based Composite Indicators by Means of Biclustering
CLADAG 2019 12-th Scientific Meeting Classification and Data Analysis Group Cassino, September 11 – 13, 2019 Book of Short Papers/Abstracts
4 Pages Posted: 29 Apr 2020
Date Written: September 2019
Abstract
Interval-based composite indicators are useful as subjectivities exist in the choices leading to the construction of a composite indicator. The interval shows the level of variation which is able to be determined by the different factors considered on the construction of the composite indicator. We will explore and analyze different results of the underlying composite indicators computed on the Monte Carlo simulations using biclustering. The results offer an understanding and explanation of the sensitivity of the composite indicator outcomes to the inputs under consideration.
Keywords: composite indicators, interval data, biclustering
JEL Classification: C43, C81, C82
Suggested Citation: Suggested Citation