Exploring Voting Blocs Within the Irish Electorate: A Mixture Modeling Approach

Files in This Item:
File Description SizeFormat 
irishpref-march07.pdf253.6 kBAdobe PDFDownload
Title: Exploring Voting Blocs Within the Irish Electorate: A Mixture Modeling Approach
Authors: Gormley, Isobel Claire
Murphy, Thomas Brendan
Permanent link: http://hdl.handle.net/10197/7122
Date: Sep-2008
Abstract: Irish elections use a voting system called proportion representation by means of a single transferable vote(PR-STV). Under this system, voters express their vote by ranking some (or all) of the candidates in order of preference. Which candidates are elected is determined through a series of counts where candidates are eliminated and surplus votes are distributed.The electorate in any election forms a heterogeneous population: that is voters with different political and ideological persuasions would be expected to have different preferences for the candidates. The purpose of this article is to establish the presence of voting bloes in the Irish electorate, to characterize these blocs and to estimate their size.A mixture modeling approach is used to explore the heterogenecity of the Irish electorate and to establish the existence of clearly defined voting blocs. The voting blocs are characterized by thier voting preferences which are described using a ranking data model. In addition the care with which voters choose lower tier preferences is estimated in the model.The methodology is used to explore data from two Irish election. Data from eight opinion polls taken during the six weeks prior to the 1997 Irish presidential election are analyzed. These data reveal the evolution of the structure of the electorate during the election campaign. In addition data that record the votes from the Dublin West constituency of the 2002 Irish general election are analyzed to reveal distinct voting blocs within the electoate these blocs are characterized by party politics, candidate profile and political ideology.
Funding Details: Irish Research Council for Science, Engineering and Technology
Type of material: Journal Article
Publisher: Taylor and Francis
Copyright (published version): 2008 American Statistical Association
Keywords: Elections;Mixture models;Ranking data;Voting blocs;Maximum-likelihood;MM algorithms
DOI: 10.1198/016214507000001049
Language: en
Status of Item: Peer reviewed
Appears in Collections:Mathematics and Statistics Research Collection

Show full item record

SCOPUSTM   
Citations 10

31
Last Week
1
Last month
checked on Jun 22, 2018

Download(s) 50

144
checked on May 25, 2018

Google ScholarTM

Check

Altmetric


This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.