Voter Transition Research Articles

Adjustment of initial estimates of voter transition probabilities to guarantee consistency and completeness

The estimation of voter shifts (stayers and switchers) between elections is an active area of research that, for decades, has attracted the interest of many scholars. The voter transitions are typically summarised in a row-standardised proportion (probability) matrix. This matrix is usually unknown, despite it being of interest to many agents, including party teams, the media and political scientists. When surveys are used to approximate this matrix, it is not uncommon for the estimated matrix to be inconsistent and even incomplete. The iterative proportional fitting algorithm solves inconsistency but cannot fix incompleteness. Hierarchical Bayesian models that combine aggregate and survey estimates can solve both problems, but are extremely complex and data-demanding. This paper details all the scenarios concerning the available information that can be reasonably considered and, within the linear programming framework, develops specific models to reach consistency and completeness. The models are, moreover, quite flexible as they allow analysts to have missing values and to introduce through weights their relative confidences in the different a priori transition proportions. The usefulness of the proposed models is illustrated with real data. Interested readers can easily use these new models with their data as they have been programmed in the function lp_apriori of the R-package lphom.

Mapping the 2020 Slovak Parliamentary Election. Analysis of Spatial Support and Voter Transition

This contribution is a complex analysis of the geographic voting patterns in the 2020 Slovak parliamentary election using methods such as Geographically Weighted Regression, Hierarchical Regression Models, and Ecological Inference. It is focused on the winner of the 2020 parliamentary election, the populist OĽaNO, and on the loser, the traditional left-wing SMER-SD – within the context of electoral support and voter transition in comparison to the 2016 parliamentary election, and in part to the 2019 presidential election. The article contributes to the underdeveloped discourse relating to the spatial support of political parties in Slovakia and finds how the selected socio-economic indicators explain the varying voting patterns. The main finding is that Slovakia is an internally heterogeneous country. The socio-demographic factors have a differentiated (either positive or negative) effect on the electoral support for Slovakian parties. As a result, voting patterns differ not only between the western and eastern parts of the country but also between districts within a common geographic area or region. This reveals the complex set of dividing lines in the country and indicates future trends in Slovakian politics.

Government Partisanship and Electoral Accountability: The Effect of Perceived Employment Situation on Partisan Vote Switching

What are the electoral impacts of perceptions of unemployment under different partisan persuasions of the government? Neither the literature on retrospective economic voting nor partisan voting has provided a compelling answer to this question. This paper addresses this puzzle by analyzing panel surveys and leveraging differences in government partisanship in two consecutive elections. I argue that negative evaluations of the employment situation induce voter transition to support a left-wing party under a right-wing government, but that such voter perceptions do not affect vote choice under a left-wing government. An analysis of a voter transition, using British Election Panel Study 1992–1997 and 1997–2001, reveals findings that support my argument. My argument suggests conditional partisan voting effects. Essentially, the effect of economic issues on vote choice is conditional on issue salience and which party “owns” the issue, namely, the varying levels of issue salience related to government partisanship.

Combining Aggregate Data and Exit Polls for the Estimation of Voter Transitions

Our objective is the estimation of voter transitions between two consecutive parliamentary elections. Usually, such analyses have been based either on individual survey data or on aggregated data. To move beyond these methods and their respective problems, we propose the application of so-called hybrid models, which combine aggregate and individual data. We use a Bayesian approach and extend a multinomial-Dirichlet model proposed in the ecological inference literature. Our new hybrid model has been implemented in the R-package eiwild (= Ecological Inference with individual-level data). Based on extensive simulations, we are able to show that our new estimator exhibits a very good estimation performance in many realistic scenarios. Application case is the voter transition between the Bavarian Regional election and the German federal elections 2013 in the Metropolitan City of Munich. Our approach is also applicable to other areas of electoral research, market research, and epidemiology.

Expressive and Strategic Behavior in Legislative Elections in Argentina

In this paper I study strategic voting behavior in the Argentine Senate election for the City of Buenos Aires in 2013. I estimate and analyze the voter transition matrix between the primary and general elections using a Bayesian hierarchical model for ecological inference, utilizing a rich data set of ballot box data. The results show that strategic behavior is not widespread among the electorate in Buenos Aires. In particular, at least 75 % of voters who had the opportunity to avoid vote wasting by behaving strategically did not. I also find high levels of vote wasting when analyzing other provinces during the same election cycle. These results suggest that these electorates might be composed of a mixture of voters with strategic and expressive motivations, where the expressive factions dominate.

A Method for the Estimation of Voter Transition Rates

Recent advances in the field of ecological inference have provided researchers with new tools to estimate voter transition rates in two‐party systems, based on contingency tables. Although some researchers have moved from the 2×2 case to the broader R×C ecological inference problem, voter transition estimation remains a difficult and tedious goal. As a result, scholars of multiparty systems still struggle with their data. In this paper we follow a new approach and we propose a new method that deals with this issue. Using two data sets, one from the French presidential elections in 2007 (first and second round) and one from the Greek parliamentary elections (2004 and 2007), we demonstrate that the proposed method provides good estimates of voter transition rates.

Party Realignment and Voter Transition in Italy, 1987-1996

Between 1987 and 1996, the Italian party system experienced a major realignment. The political alternatives that dominated the postwar period dissolved, and new party and voter alignments emerged. This analysis employs a recently compiled data archive and a new ecological inference technique to examine voter transitions during the period. The disintegration of the ruling party coalition and the appearance of new party alternatives from the center of the analysis. The research highlights the importance of nonvoters, a relatively recent phenomenon in Italian elections, as a precursor of pending party change as well as holding the key to a resolution of the current flux. The new ecological analysis technique generates more robust results than previous techniques and also avoids the pitfalls of survey research.

On ecological regression and ridge estimation

This paper focuses on the development of an ecological regression approach for voter transition estimation, avoiding the arbitrary assumptions in Goodman's classical model of ecological regression (Goodman [1959]). In doing this, we further develop previous attempts made at the ridge regression approach, by applying a modified generalized ridge estimator. To illustrate the application of the proposed estimation technique, we estimate the transition probabilities in the last two Swedish elections on a local level.

Estimating voter transitions by ecological regression

This article focuses on the development of an ecological regression approach for voter transition estimation, avoiding the arbitrary assumptions in Goodman's classical model of ecological regression (Goodman, 1959). In doing this, we further develop previous attempts made at the ridge regression approach in ecological regression (made, for example, by Miller (1972), Brown and Payne (1975)). To illustrate the application of the proposed estimation technique, we include a comparative study based on a set of actual election data, where we analyse whether our own estimates of transition probabilities are congruent with patterns obtained from other models. We find that the ecological regression model using the modified estimator results in estimates which are superior to those obtained from survey data.

By-election exit polls

With the rise of the Alliance parties, by-elections have become an important focus of the media’s coverage of the political scene in the UK. The television companies and newspapers regularly commission polls to predict the shares of the vote won by each party standing in the by-election. These polls take two forms: voting intention polls of the constituency electorate are carried out before polling day and so-called ‘exit’ polls on the election day itself when voters are interviewed as they leave the polling stations. In this paper we describe the statistical basis of the sampling scheme and estimation method developed for use by the BBC TV Newsnight programme in a series of ten byelection exit polls carried out in the period November 198 1 to May 1986. A new method of estimation of party shares of the vote, based on voter movements from the previous general election is described. This method is shown to perform generally better than the traditional method based on declared vote. It has potential application to the general problem of estimation of party shares from any type of voting intention poll. We first discuss the problems of carrying out by-election exit polls. The sampling scheme and estimation method developed are described in Section 2. Section 3 compares the performance of the voter transition method for the estimation of party shares with the traditional merhod and evaluates the contribution of the various components of the scheme to its success.

Estimation of the voter transition matrix

This paper is concerned with an estimation of the voter transition matrix using programming methods. Thus, applying the Minimum Absolute Deviations (MAD) and the Restricted Least Squares (RLS) principles, the corresponding estimator has been determined, where the first one seems to be more efficient than the second.

Spatial continuity and individual variability: A review of recent work on the geography of electoral change

Analyses have shown that the results of a series of general elections display considerable stability in the geography of voting patterns over time. Further, it has been suggested that the change between two electrons is similar in all places. This paper challenges the latter findings, using data from Great Britain and New Zealand. It is shown that even if there were a pattern of uniform swing, this would be produced by spatial variations in voter transition matrices. A review of analyses of those variations suggests the important roles of the neighbourhood effect, campaign spending, tactical voting, sectional effects, and migration as influences on voter behaviour.

The Geography of Electoral Change: An Illustration of an Estimating Procedure

A major problem facing students of the geography of electoral change is the paucity of data. To circumvent the difficulties of studying net change only, a method has been developed to provide estimates of voter transition matrices for individual spatial units within a country. This method has been applied to New Zealand for the inter- electoral period 1972-1975. The results are outlined and ana- lysed here; they suggest clear sectional variations within New Zealand in the magnitude of inter-party movements, reflecting differences between the two main islands and between metro- politan, urban and rural areas. Studies in electoral geography can be divided into three main types (Taylor, 1978). The first

Short-term electoral change in England: estimates of its spatial variation

A method of estimating the entries of a voter transition matrix, at the constituency level, is used to provide better information on short-term electoral change than previously available. Inter-constituency variations are regressed against four sets of variables, producing encouraging tests of models of electoral change.

A Note on the Estimation of Voter Transition Probabilities

SUMMARY This paper utilizes the results of a panel survey, conducted after the General Elections of February and October 1974, to obtain the estimated voter transition probabilities for constituencies contested on each occasion by candidates representing the Conservative, Labour and Liberal parties. The panel estimates are compared with those derived by McCarthy and Ryan (1977) who used a quadratic programming method. Although the panel results underestimate the proportion of the electorate who did not vote, they provide clear evidence that the quadratic programming oversimplifies the pattern of voting change. The panel results also show clearly that the pattern of voting change between two elections is affected by the relative party strengths in the first election.

Estimates of Voter Transition Probabilities from the British General Elections of 1974

Estimates of Voter Transition Probabilities from the British General Elections of 1974

Building Voter Transition Models from Aggregate Data

Building Voter Transition Models from Aggregate Data