Predicting popular vote shares at Us presidential elections

Election forecasting in modern democracies faces significant challenges, including increasing survey nonresponse and selection bias. Added to this are the limitations of current predictive approaches. While structural models focus solely on macro-level variables-such as economic conditions and leade...

Full description

Bibliographic Details
Author: Camatarri, Stefano|||0000-0002-7233-5876
Format: article
Publication Date:2024
Country:España
Institution:Universitat Autònoma de Barcelona
Repository:Dipòsit Digital de Documents de la UAB
Language:English
OAI Identifier:oai:ddd.uab.cat:303023
Online Access:https://ddd.uab.cat/record/303023
https://dx.doi.org/urn:doi:10.1017/S1049096524000933
Access Level:Open access
Keyword:Election forecasting
Voting intentions
US Presidential elections
Regression analysis
ANES
Description
Summary:Election forecasting in modern democracies faces significant challenges, including increasing survey nonresponse and selection bias. Added to this are the limitations of current predictive approaches. While structural models focus solely on macro-level variables-such as economic conditions and leader popularity-thereby overlooking the importance of individual-level factors, survey-based aggregation methods often rely on intuitive procedures that lack theoretical foundations. To address these gaps, this contribution proposes a combined logistic regression approach (both standard and Bayesian) that leverages voter-level data and incorporates a theorybased specification. By testing these models on recent waves of the American National Election Studies (ANES) Time Series, this study demonstrates that the proposed approach yields notably accurate predictions of Republican popular support in each election.