A Bayesian Networks Approach for Analyzing Voting Behavior

Miguel Calvin and Pilar Rey del Castillo

No 10855, CESifo Working Paper Series from CESifo

Abstract: The problem of finding the factors influencing voting behavior is of crucial interest in political science and is frequently analyzed in books and articles. But there are not so many studies whose supporting information comes from official registers. This work uses official vote records in Spain matched to other files containing the values of some determinants of voting behavior at a previously unexplored level of disaggregation. The statistical relationships among the participation, the vote for parties and some socio-economic variables are analyzed by means of Gaussian Bayesian Networks. These networks, developed by the machine learning community, are built from data including only the dependencies among the variables needed to explain the data by maximizing the likelihood of the underlying probabilistic Gaussian model. The results are simple, sparse, and non-redundant graph representations encoding the complex structure of the data. The generated structure of dependencies confirms many previously studied influences, but it can also discover unreported ones such as the proportion of foreign population on all vote variables.

Keywords: Bayesian networks; Gaussian distributions; voting behaviour; elections; voter turnout; political participation (search for similar items in EconPapers)
JEL-codes: C46 D31 D72 D91 (search for similar items in EconPapers)
Date: 2023
New Economics Papers: this item is included in nep-big, nep-cdm, nep-net and nep-pol
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.cesifo.org/DocDL/cesifo1_wp10855.pdf (application/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:ces:ceswps:_10855

Access Statistics for this paper

More papers in CESifo Working Paper Series from CESifo Contact information at EDIRC.
Bibliographic data for series maintained by Klaus Wohlrabe ().