Abstract
This paper, issued from the Cartelec project, raises a methodological issue regarding ecological inference. Studying abstention in two recent French elections in the Parisian agglomeration, a linear regression is launched on three different levels of aggregation: from the finest one (polling station), through cities, to electoral districts (circonscriptions). Tests on multicollinearity clearly indicate that employing the finest level of aggregation allows more variables to be significant, enhances the explanatory power of the model, and improves the collinearity amongst the dependent variables.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
Abstention, measured in percentages of the inscrits, was 16.22 % (national level) in 2007 versus 53.64 % in 2010. For the space studied here, the gap is even higher (14 % in 2007 and 55.79 % in 2010).
Being inscrit on the electoral list is mandatory for voting. The inscription is theoretically an obligation for all French citizens, but constraint has never been used, and the non-inscription rate is estimated around 7–9% of the French adult population (Braconnier and Dormagen 2007a).
Source: INSEE National census, 2007.
Accomplir son devoir électoral.
For people knowing the French educational system: low level means a diploma from CAP to BEP, and high level means (the name being a little abusive for the youngest generations) Baccalauréat and above.
In 2008, Paris had 2,590,000 inhabitants and the second largest city of la petite couronne is Boulogne-Billancourt with only 109,000 inhabitants. The largest Parisian arrondissement in population is the 15th, with 238,000 persons.
In France, if we consider all elections on a national scale, excluding referendums, the highest rate of abstention was in the 2009 Européennes election, at 59.37 % of the inscrits.
The percentage of French in the population is 84.84 %, the foreigners are 15.16 %, and the immigrants, 20.48 %. The total is of course more than 100 %.
The percentage of no diploma in the population is 13.01 %, the percentage of people holding a title form a CAP to a BEP are 18.91 %, and the ones olding a BAC or more are 38.20 %. All the remaining population out of this percentages is still studying.
The percentage of owners in the population is 17.45 %, the renters are 25.73 %, and the people benefiting from free housing, 1.81 %.
The percentage of young in the population is 9.86 %, the people in their working age are 55.60 %, and the seniors, that is the old, 12.84 %.
References
Braconnier, C., Dormagen, J.-Y.: Ségrégation sociale et ségrégation politique. Non inscrits, mal inscrits et abstentionnistes, Centre d’analyse stratégique 11, 6–61 (2007a)
Braconnier, C., Dormagen, J.Y.: La démocratie de l’abstention. Aux origines de la démobilisation électorale en milieu populaire. Gallimard, Paris (2007b)
Chatterjee, S., Hadi, A.S., Price, B.: Regression Analysis by Example. Wiley, New York (2000)
Hamilton, L.C.: Statistics with STATA. Brooks/Cole, Toronto (2009)
Héran, F.: Le nouveau désordre électoral. In: Cautrès, B., Mayer, N. (eds.) Voter toujours, parfois..ou jamais, pp. 351–357. Presses de Sciences Po, Paris (2004)
Lancelot, A.: L’abstentionnisme électoral en France. Armand Colin, Paris (1968)
Leahy, K.: Multicollinearity: when the solution is the problem. In: Rud, O.P. (ed.) Data Mining Cookbook, pp. 106–108. Wiley, New York (2001)
Lewis-Beck, M.S.: Applied Regression. An Introduction. Sage Publications, Newbury Park (1980)
Mooney, C.Z., Duval, R.D.: Bootstrapping: A Nonparametric Approach to Statistical Inference. Sage Publications, Newbury Park (1993)
Morris, J.D.: Ridge regression and some alternative weighting techniques: a comment on Darlington. Psychol. Bull. 91, 203–210 (1982)
Oumlil, A.B., Balloun, J.L.: Levels of aggregation: a conceptual model. Qual. Quant. 32, 109–117 (1998)
Pagel, M.D., Lunneberg, C.E.: Empirical evaluation of ridge regression. Psychol. Bull. 97, 342–355 (1985)
Percheron, A., Subileau, F., Toinet, M.-F.: Non-inscription, abstention et vote blanc et nul en France. Espace, populations, sociétés 3, 511–521 (1987)
Rivière, J.: Vote et géographie des inégalités sociales : Paris et sa petite couronne, Métropolitiques. http://www.metropolitiques.eu/Vote-et-geographie-des-inegalites.html (2012)
Robinson, W.S.: Ecological correlations and the behaviour of individuals. Am. Sociol. Rev. 15(3), 351–357 (1950)
Selb, P., Simon, M.: Voter overrepresentation, vote misreporting, and turnout bias in postelection surveys. Paper presented at the First European conference on comparative electoral research, Sofia, December 1–3 (2011)
Subileau, F., Toinet, M.-F.: Les chemins de l’abstention : une comparaison franco-américaine. La Découverte, Paris (1993)
Upton, G., Cook, I.: Oxford Dictionary of Statistics. Oxford University Press, New York (2008)
Acknowledgments
This paper benefited from the inputs of the project Cartelec members: L. Beauguitte, S. Bourdin, M. Bussi, B. Cautrès, C. Colange, S. Freire-Diaz, A. Jadot, J. Rivière, and L. Russo.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Russo, L., Beauguitte, L. Aggregation level matters: evidence from french electoral data. Qual Quant 48, 923–938 (2014). https://doi.org/10.1007/s11135-012-9814-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11135-012-9814-0