Dynamic Bayesian Forecasting of Presidential Elections in the States

Linzer, Drew A.

doi:10.1080/01621459.2012.737735

Cited by 108 publications

(111 citation statements)

References 53 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…There are two important arguments to preclude that assumption: (i) Even though it may be argued that factors like campaign events (e.g., media coverage, television advertising, candidate evaluation; see [25,26,53]) and polls could be important in terms of shaping strategic behavior (as understood in the game theory literature), we observe that not all events have the potential to do that. Polls, for instance, may have large fluctuations during campaigns and yet the opinions of voters might change very marginally over time, suggesting that polls may not affect voting behavior in an important way [38]. In addition, and more importantly, factors that influence strategic behavior may be pointless in a study of the impact of nonanticipatable events (e.g., a sudden dimensionality reduction) like ours (see e.g., [41]).…”

Section: Changing Space Dimensionalitymentioning

confidence: 99%

Political Spaces, Dimensionality Decline and Party Competition

García-Díaz

Zambrana-Cruz

Witteloostuijn

2013

Advs. Complex Syst.

View full text Add to dashboard Cite

We built a computational model of political party competition in order to gain insight into the effect of the decrease in the number of relevant political issues (dimensions), and the change of their relative importance, on the number of surviving political parties, their strategy performance, and the degree of political party fragmentation. Particularly, we find that when there is a dimensionality reduction (i.e., a change from a two-dimensional issue space to a one-dimensional one, or, a substantial decrement in one of the issue's relative importance with respect to the other), the number of political parties declines, as does the overall degree of party fragmentation in the system. Regarding party strategies, we observe that, after the dimensionality reduction, (i) the inert parties tend to improve their performance in terms of party numbers (i.e., more inert parties survive, relatively * Corresponding author. C. García-Díaz, G. Zambrana-Cruz and A. van Witteloostuijn speaking); (ii) the population of large-size seekers declines, (iii) the few large-size seeker survivors, in general, cushion their increased mortality hazard with increased size (i.e., increased number of supporters); and, finally, (iv) the mortality hazard increases with distance to the mean voter spot.

show abstract

Section: Changing Space Dimensionalitymentioning

confidence: 99%

Political Spaces, Dimensionality Decline and Party Competition

García-Díaz

Zambrana-Cruz

Witteloostuijn

2013

Advs. Complex Syst.

View full text Add to dashboard Cite

show abstract

“…The dynamic linear model (DLM) has become the staple horse technique for polling based forecasts (Pickup and Johnston, 2007;Fisher et al, 2011;Linzer, 2013) and it is therefore worth going over the technique in some detail.…”

Section: Election Forecasts Through Polling-based Methodsmentioning

confidence: 99%

Picking the winner(s): Forecasting elections in multiparty systems

Walther

2015

Electoral Studies

View full text Add to dashboard Cite

a b s t r a c tFrom the 1970s onwards, a wide range of forecasting techniques have been developed in the literature on electoral forecasting. However, these models have primarily been applied in two-party, presidential democracies, with the US being by far the most popular country to investigate. The question thus arises whether the same techniques that have proved successful in this context can also be applied to the more complex, multiparty democracies in northern Europe. This paper seeks to answer this question and in the process makes two main contributions. Firstly, the popular dynamic linear model (Jackman, 2005) is tried and tested in Germany and Sweden where it is shown that reasonable forecasts can be made despite the complexity of the systems and the emergence of new parties. A novelty is then introduced when cyclical changes in party support are modelled through a seasonal component. This extension of the dynamic linear model helps to significantly lower the error in early forecasts and is thus something that could be useful in future applications of the model.

show abstract

“…Although producing accurate predictions of future events is not the primary goal in most of the social sciences, recent years have witnessed the spread of systematic forecasting from more traditional topics, such as GDP growth and unemployment, to many new domains, including elections (e.g., Linzer, 2013), political instability (e.g., Goldstone et al, 2010), and mass killings (Ulfelder, 2012). Several factors have motivated this trend.…”

Section: Introductionmentioning

confidence: 99%