We propose a novel method and algorithm for the analysis and clustering of mixed-type data using a hierarchical approach based on Forward Search. In our procedure, the identification of groups is based on the identification of similar trajectories and then linked to very intuitive two-dimensional maps. The proposed algorithm can use different measures for the calculation of distance in the case of mixed-type data, such as Gower’s metric and Related metric scaling. A key feature of our algorithm is its ability to discard redundant information from a given set of variables. The practical usefulness of the algorithm is illustrated through two applications of high relevance for empirical economic research. The first one focuses on comparing different indicators of environmental policy stringency in different countries. The second one applies our procedure to identify clusters of countries based on information regarding their institutional characteristics.
Robust multivariate analysis for mixed-type data: Novel algorithm and its practical application in socio-economic research / A. Grané, S. Salini, E. Verdolini. - In: SOCIO-ECONOMIC PLANNING SCIENCES. - ISSN 0038-0121. - (2020 Jun 23). [Epub ahead of print] [10.1016/j.seps.2020.100907]
Robust multivariate analysis for mixed-type data: Novel algorithm and its practical application in socio-economic research
S. Salini
;
2020
Abstract
We propose a novel method and algorithm for the analysis and clustering of mixed-type data using a hierarchical approach based on Forward Search. In our procedure, the identification of groups is based on the identification of similar trajectories and then linked to very intuitive two-dimensional maps. The proposed algorithm can use different measures for the calculation of distance in the case of mixed-type data, such as Gower’s metric and Related metric scaling. A key feature of our algorithm is its ability to discard redundant information from a given set of variables. The practical usefulness of the algorithm is illustrated through two applications of high relevance for empirical economic research. The first one focuses on comparing different indicators of environmental policy stringency in different countries. The second one applies our procedure to identify clusters of countries based on information regarding their institutional characteristics.File | Dimensione | Formato | |
---|---|---|---|
socio-eco-planning_science2020.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
2.57 MB
Formato
Adobe PDF
|
2.57 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Grane_Salini_Verdolini_REVISION-5.pdf
Open Access dal 24/06/2022
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
1.03 MB
Formato
Adobe PDF
|
1.03 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.