Måns Magnusson: Botten Ada: Bayesian Aggregation of Opinion Polls for Inference and Forecasting

Abstract

 Political opinions are often measured with opinion polls, and in some situations, such as party preferences, a large number of measurements are available over time. We introduce a new, longitudinal model for opinion polls with multiple, correlated party proportions, as is common in multi-party democratic systems. The model combines multiple measurement effects, such as house bias and design effects, and introduces a new measurement component we call industry bias, a bias common to all polling houses.

We show the model's performance in Sweden to estimate party preference over more than 20 years. We also used the model to predict the Swedish election in 2022 with the major Swedish newspaper Svenska Dagbladet, and the final point prediction came closer than any other poll, prediction, or poll of polls. However, much research is still needed, and the area poses many different challenges.