The analysis of voter transitions is an important area of electoral studies. A main strategy is to use aggregate data provided by the offices of statistics regarding districts, precincts, communities etc. and to rely on ecological inference. Ecological inference, however, is plagued by the well-known indeterminacy problem. In this article, we present the so far most extensive systematic empirical comparison of commonly used approaches for ecological inference of the analysis of voter transitions. Our evaluation is based on diverse simulations for multiple assumptions and scenarios. Based on recent election data for the German metropolitan city Munich, we are able to show that an application of the hierarchical multinomial-Dirichlet model, which is implemented in the R-library eiPack, exhibits the best overall estimation performance. Other prominent approaches frequently used by practitioners, e.g. the Thomsen logit approach, proved to be inconsistent. Furthermore, we demonstrate that appropriate data preprocessing is crucial for achieving reliable results.

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.

No abstract

No abstract

No abstract