Publication:
Robust multivariate analysis for mixed-type data: Novel algorithm and its practical application in socio-economic research

Loading...
Thumbnail Image
Identifiers
Publication date
2021-02-01
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
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.
Description
Keywords
Forward search, Mixed type data, Outliers, Robustness, Redundant information, Clustering
Bibliographic citation
Grané, A., Salini, S., & Verdolini, E. (2021). Robust multivariate analysis for mixed-type data: Novel algorithm and its practical application in socio-economic research. Socio-Economic Planning Sciences, 73, p. 100907