The number of clusters on trust

In this work we analyse the perfomance of a new Expectation Maximization (EM) clustering approach. This method is based on the Minimum Message Lenght (MML) criterion and simultaneously yields clustering of categorical data and the number of clusters. We group European citizens based on their trust i...

Full description

Bibliographic Details
Main Author: Silvestre, Cláudia (author)
Other Authors: Cardoso, Margarida (author), Figueiredo, Mário (author)
Format: conferenceObject
Language:eng
Published: 2017
Subjects:
Categorical data
Clustering
EM-MML algorithm
European Social Survey
Finite mixture models
Online Access:http://hdl.handle.net/10400.21/7671
Country:Portugal
Oai:oai:repositorio.ipl.pt:10400.21/7671
Description
Summary:In this work we analyse the perfomance of a new Expectation Maximization (EM) clustering approach. This method is based on the Minimum Message Lenght (MML) criterion and simultaneously yields clustering of categorical data and the number of clusters. We group European citizens based on their trust in institutions, using Europen Social Survey data. The results obtained illustrate the parsimony, the cohesion-separation and stability of the EM-MML solutions, when compared to traditional information criteria EM based approaches.

Similar Items