Abstract
The general purpose of this work consists in to relate the statistical methods for the estimation of voter transitions rates based on aggregate data, with the problem of inferring the composition of the electorate in a democratic system in seven categories of voters once the second of two consecutive voting processes has been carried out. To know the electorate composition between stable and unstable voters is a matter of relevance to sociology and political science regarding comparative research. Available options to infer these values—electoral polls and panel surveys—present reliability issues arising from lack of recall or concealing on the voting behavior. In view of this situation, we propose an original estimation strategy consisting in to locate the unknown quantities within of a matrix whose sums of entries by rows and columns are known; based on this, such magnitudes can be estimated resorting to Ecological inference methods. The proposal was applied to the case of competition between political conglomerates in Chile for the period 1993–2009, using two types of estimation methods with aggregate data available in the free software R. One of those methods rendered results consistent with previous evidence proceeding from polls. We conclude that the proposed strategy can be replicable on a larger-scale application, even though these methods must, in parallel, remain subject to evaluation and improvement.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Availability of data and material
\(\bullet\) doi: https://doi.org/10.13140/RG.2.2.17057.12643. \(\bullet\) doi: https://doi.org/10.13140/RG.2.2.31366.80964.
\(\bullet\) doi: https://doi.org/10.13140/RG.2.2.17177.03686\(\bullet\) doi: https://doi.org/10.13140/RG.2.2.35561.11365. \(\bullet\) doi: https://doi.org/10.13140/RG.2.2.11234.15045. \(\bullet\) doi: https://doi.org/10.13140/RG.2.2.17945.03683.
Code availability
Notes
Taking into account the eventual preponderance of any of the before mentioned types of electors it can be determined the preponderance of one specific type of voter-party linkage (e.g. programmatic, clientelism, etc.), or alternatively its diversification in the case that neither of the categories resulted being predominant.
In systems with high levels of electoral volatility, the ‘agents’ of the democratic system (political parties or political conglomerates) have fewer incentives to create political representation projects that provide certain governability in the foreseeable future.
The polls either pre or post the second of the voting events do not incorporate the behavior of former voters. On the other hand, panel samples would require to be actualize permanently in order to represent the behavior of the new voters.
This would have happened supposedly if we took as an example the presence of two options of representation A and B respectively in two successive voting events, besides the absence of change in the electoral register, which in both cases concentrated a 50% of the preferences in the first instance of this process, and would have lost the totality of their electorate, in favor of another option in the second of the voting events.
The use of the term ‘ecological’ comes originally from the work of Robinson (1950). Possibly, the choise of this adjective had in mind the etymological root of such term: from the Greek: oikos/ home and logos/ science. It is possible then that by choosing to use this term it was intended to highlight the belonging of the individuals to their respective local geographies; even though this does not result to be really clear from reading the available literature.
This strategy is employed today to distinguish ‘type A volatility’, which is identified as the one originated by the entry or outing of agents of representation, from ‘type B volatility’, which is produced by changes in vote shares obtained by the representation agents present in both electoral processes (Powel and Tucker 2013).
After the period here analyzed the electoral system was modified in such a way that the inscription in the electoral register became automatic, from the moment someone became of legal age, and the vote became voluntary.
The application of the Binominal system had the desired purpose of concentrating the parliamentary representation between the two main political coalitions during this period: ‘Concertación of Parties for Democracy’ and the ‘Alliance for Chile’, previously known as the ‘Union for Chile’.
The majority of these data were obtained via the physical books from each year that exist in the dependencies of the SERVEL.
It is important to remember that we were dealing with a System with voluntary inscription and mandatory vote.
In Chile, there is currently a consulting organism dedicated to conducting public opinion surveys, as well as of electoral nature, called “Centro de Estudios de la Realidad Contemporánea” (CERC, for its acronym in Spanish), which, for each election contained in the series analyzed here (1993–2019) conducted a nationally representative polls in which voters were consulted about their voting behavior, as well as their electoral behavior in the previous election. Today this organization is associated with the private company called “Mori” (see: http://morichile.cl/areas-de-investigacion/politica/). More details about the methodological characteristics of such polls can be found in the aforementioned work by Avendaño and Sandoval (2013), although it should be noted that is written in Spanish.
Furthermore, the results were pondered in relation to the voting results from the second consecutive voting in each case.
For the remaining periods, the estimated figures are less coincident. The increment of the political disaffection occurred in the country can have produced a lesser predisposition to answer electoral polls, distorting then the estimations, or conducing to a greater masking of the behavior from the real vote. Whichever the case may be, this does not constitute a matter that can be settled with the kind of evidence here provided.
References
Andreadis, I., Chadjipadelis, T.G.: A method for the estimation of voter transition rates. J. Elect. Public Opin. Parties 19(2), 203–218 (2009)
Avendaño, O., Sandoval, P.: Volatilidad electoral y Desafección política en las Elecciones parlamentarias chilenas 1993–2009. Revista de Sociología de la Universidad de Chile 28, 141–164 (2013)
Bartolini, S., Mair, P.: Identity, competition, and Electoral availability. In: The Stabilisation of European electorates 1885–1985. Cambridge University Press, Cambridge (1990)
Casal Bértoa, F.: The three waves of party system institutionalisation studies: a multi- or uni-dimensional concept? Polit. Stud. Rev. 16(1), 60–72 (2018)
Casal Bértoa, F., Deegan-Krause, K., Haughton, T.: The volatility of volatility: measuring change in party vote shares. Elect. Stud. 50, 142–156 (2017)
Chiaramonte, A., Emanuele, V.: Party system volatility, regeneration and de-institutionalization in Western Europe (1945–2015). Party Polit. 23(4), 376–388 (2017)
Corominas, A., Lusa, A., Calvet, M.D.: Computing voter transitions: the elections for the Catalan Parliament, from 2010 to 2012. J. Ind. Eng. Manag. 8(1), 122–136 (2015)
Crewe, I., Denver, D.: Electoral change in Western democracies. Croom Helm, London (1985)
Dassonneville, R.: Volatile voters, short-term choices? An analysis of the vote choice determinants of stable and volatile voters in Great Britain. J. Elect. Public Opin. Part. 26(3), 273–292 (2016)
Duncan, O., Davis, B.: An alternative to ecological correlation. Am. Sociol. Rev. 18(6), 665–666 (1953)
Freedman, D.A.: Ecological inference and the ecological fallacy. In: Smelser, N.J., Baltes, P.B. (eds.) International Encyclopedia of the Social and Behavioral Sciences, pp. 4027–4030. Elsevier, New York (2001)
Forcina, A., Pellegrino, D.: Estimation of voter transitions and the ecological fallacy. Qual. Quant. 53, 1859–1874 (2019)
Goodman, L.: Ecological regression and behaviour of individuals. Am. Sociol. Rev. 18(6), 663–664 (1953)
Goodman, L.: Some alternatives to ecological correlation. Am. J. Sociol. 64(6), 610–625 (1959)
Greiner, D.J., Quinn, K.M.: RxC ecological inference: bounds, correlations, flexibility and transparency of assumptions. J. R. Stat. Soc. A. 172 part.1, 67–81 (2009)
King, G.: A solution to the ecological inference problem. Reconstructing individual behaviour from aggregate data. Princeton University Press, Princeton, NJ (1997)
King, G., Rosen, O., Tanner, M.A.: Binomial-beta hierarchical models for ecological inference. Sociol. Methods Res. 28(1), 61–90 (1999)
King, G., Rosen, O., Tanner, M.A.: Ecological Inference. New Methodological Strategies. Cambridge University Press, New York (2004)
Klima, A., Thurner, P.W., Molnar, C., Schlesinger, T., Küchenhoff, H.: Estimation of voter transitions based on ecological inference: an empirical assessment of different approaches. AStA Adv. Stat. Anal. 100, 133–159 (2016)
Klima, A., Thurner, P.W., Schlesinger, T., Küchenhoff, H.: Combining aggregate data and exit polls for the estimation of voter transitions. Sociol. Methods. Res. 48(2), 296–325 (2019)
Lau, O., Moore, R.T., Kellermann, M.: eiPack: RxC ecological inference and higher-dimension data management. R News 7(2), 43–47 (2007)
Luna, J.P.: Party system institutionalization. Do we need a new concept? Stud. Comp. Int. Dev. 4(49), 403–425 (2014)
Luna, J.P., Altman, D.: Uprooted but stable. Chilean party system and the concept of party system institutionalization. Lat. Am. Polit. Soc. 56(2), 1–28 (2011)
Mainwaring, S., Scully, T.: Building Democratic Institutions: Party Systems in Latin America. Stanford University Press, Stanford (1995)
Mainwaring, S., Torcal, M.: Party system institutionalization and party system theory after the third wave of democratization. In: Katz, R.S., Crotty, W. (eds.) Handbook of Party Politics, pp. 204–227. Sage, London (2006)
Mainwaring, S., Zoco, E.: Political sequences and stabilization of interparty competition: electoral volatility in old and new democracies. Party Polit. 13(152), 155–178 (2007)
Pavia, J.M.: ei. Datasets: real data sets for assessing ecological inference algorithms. Soc. Sci. Comput. Rev. 1–14 (2021)
Pedersen, M.N.: The dynamics of West European party systems: changing patterns of electoral volatility. Eur. J. Polit. Res. 7, 1–26 (1979)
Plesia, C., De Sio, L.: An evaluation of the performance and suitability of RxC methods for ecological inference with known true values. Qual. Quant. 52, 669–683 (2018)
Powel, E.N., Tucker, J.: Revisiting electoral volatility in post comunist countries: new data, new results and new approaches. Brit. J. Polit. Sci. 44, 123–147 (2013)
Robinson, W.S.: Ecological correlations and the behavior of individuals. Am. Sociol. Rev. 15(3), 351–357 (1950)
Rosen, O., Jiang, W., King, G., Tanner, M.A.: Bayesian and frequentist inference for ecological inference: the RxC case. Stat. Neerl. 55, 134–156 (2001)
Russo, L.: Estimating floating voters: a comparison between the ecological inference and the survey methods. Qual. Quant. 28, 1667–1683 (2014)
Russo, L., Beauguitte, L.: Aggregation level matters: evidence from French electoral data. Qual. Quant. 48(2), 923–938 (2014)
Sani, G.: Los desplazamientos del electorado: anatomía del cambio. In: Linz, J., Montero, J.R. (eds.) Crisis y cambio: electores y partidos en la España de los años ochenta, pp. 1–26. Centro de Estudios Constitucionales, Madrid (1986)
Torcal, M.: Institucionalización de sistemas de partidos. Concepto, medición, procesos y consecuencias. In: Torcal, M. (ed.) Sistemas de partidos en América Latina. Causas y consecuencias de un equilibrio inestable, pp. 7–18. Antrophos, Barcelona (2015)
Van der Meer, T.G.G., van Elsas, E., Lubbe, R., van der Brug, W.: Are volatile voters erratic, whimsical or seriously picky? A panel study of 58 waves into the nature of electoral volatility (The Netherlands 2006–2010). Party Polit. 21(1), 100–114 (2015)
Van der Ploeg, C., Van de Pool, F., Kampen, J.: A Comparison of Different Estimation Methods of voter transtions with an Application in the Dutch National Elections of 2003 and 2006. Statistics Netherlands, The Hague/Heerlen, Discussion paper (2005)
Funding
Not applicable.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Sandoval, P., Ojeda, S. Estimation of electoral volatility parameters employing ecological inference methods. Qual Quant 57, 405–426 (2023). https://doi.org/10.1007/s11135-022-01367-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11135-022-01367-z