Arndt Leininger

Vintage errors: do real-time economic data improve election forecasts?

Economic performance is a key component of most election forecasts. When fitting models, however, most forecasters unwittingly assume that the actual state of the economy, a state best estimated by the multiple periodic revisions to official macroeconomic statistics, drives voter behavior. The difference in macroeconomic estimates between revised and original data vintages can be substantial, commonly over 100% (two-fold) for economic growth estimates, making the choice of which data release to use important for the predictive validity of a model. We systematically compare the predictions of four forecasting models for numerous US presidential elections using real-time and vintage data. We find that newer data are not better data for election forecasting: forecasting error increases with data revisions. This result suggests that voter perceptions of economic growth are influenced more by media reports about the economy, which are based on initial economic estimates, than by the actual state of the economy.

Die Erfolge der AfD und die Wahlbeteiligung: Gibt es einen Zusammenhang?

Seit die Alternative für Deutschland (AfD) erstmals zur Bundestagswahl 2013 antrat, nahm sie an allen darauffolgenden Landtagswahlen sowie der Europawahl 2014 teil und erzielte dabei teils beachtliche Erfolge. Gleichzeitig stieg die Wahlbeteiligung in einigen dieser Wahlen deutlich an. Der vorliegende Beitrag ist vor diesem Hintergrund einerseits motiviert durch die Vermutung, dass die AfD von der gestiegenen Wahlbeteiligung profitiert hat, und andererseits von der Behauptung, dass die AfD dazu beitrug, die Wahlbeteiligung zu steigern.

Eine länderbasierte Prognose zur Bundestagswahl 2017

A Länder-based Forecast of the 2017 German Bundestag Election Abstract: When elections are distant, polls are poor predictors. Too few voters are paying attention and too much can change before election day. Structural models can establish baseline expectations but suffer from high uncertainty and underspecification imposed by small samples. We present an early forecast of the 2017 Bundestag election results for individual parties that leverages economic and political data as well as state parliament (Landtag) election results in the German states (Länder) to sidestep these shortcomings. A linear random effects model provides our estimates. Länder elections are dispersed over the calendar and offer the advantage of capturing both actual voter preferences and new political issues. We argue that this approach offers a promising method for early forecasts when polls are not informative.