A multidimensional unfolding technique that is not prone to degener-ate solutions and is based on multidimensional scaling of a complete data matrix isproposed. We adopt the strategy of augmenting the data matrix, trying to build acomplete dissimilarity matrix, by using Copulas-based association measures amongrankings (the individuals), and between rankings and objects (namely, a rank-orderrepresentation of the objects through tied rankings). The proposed technique leads toacceptable recovery of given preference structures.
|Titolo:||Copula-based non-metric unfolding onaugmented data matrix|
|Data di pubblicazione:||2019|
|Appare nelle tipologie:||04.01 - Contributo in atti di convegno|