Improving Discretization Exploiting Dependence Structure

Daniela Marella, Mauro Mezzini and Paola Vicard ()

No 199, Departmental Working Papers of Economics - University 'Roma Tre' from Department of Economics - University Roma Tre

Abstract: Bayesian networks are multivariate statistical models using a directed acyclic graph to represent statistical dependencies among variables. When dealing with Bayesian Networks it is common to assume that all the variables are discrete. This is not often the case in many real contexts where also continuous variables are observed. A common solution consists in discretizing the continuous variables. In this paper we propose a discretization algorithm based on the Kullback-Leibler divergence measure. Formally, we deal with the problem of discretizing a continuous variable Y conditionally on its parents. We show that such a problem is polynomially solvable. A simulation study is finally performed.

Keywords: Discretization; Kullback-Leibler divergence measure; Bayesian Networks (search for similar items in EconPapers)
JEL-codes: C10 C18 (search for similar items in EconPapers)
Date: 2015-01
New Economics Papers: this item is included in nep-ecm
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://dipeco.uniroma3.it/db/docs/WP%20199.pdf

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rtr:wpaper:0199

Access Statistics for this paper

More papers in Departmental Working Papers of Economics - University 'Roma Tre' from Department of Economics - University Roma Tre Via Silvio d'Amico 77, - 00145 Rome Italy. Contact information at EDIRC.
Bibliographic data for series maintained by Telephone for information ().