Science University Research Symposium (SURS)
Publication Date
Fall 11-4-2024
College
Sciences and Mathematics, College of
Department
Math and Computer Science, Department of
SURS Faculty Advisor
Dr. Christina Davis
Presentation Type
Poster Presentation
Abstract
This study adapts Abramowitz's Time-for-Change model to a state-level framework to forecast the 2024 U.S. presidential election. The Time-for-Change model’s focus on the popular vote has become less relevant in recent years, given the growing divergence between popular vote outcomes and electoral college results. Our model addresses these issues by adapting the original Time-for-Change predictors (presidential approval rating, GDP, and time in office) to the state level. Using data from five election cycles (2004–2020), we employ an Ordinary Least Squares (OLS) regression to predict incumbent two-party vote share. Unlike the original model, state-level GDP and incumbency duration were found to be non-significant predictors, potentially highlighting the shifting priorities of voters. Our model achieves an R^2 of 0.9416 and projects a victory for former President Trump, with wins in 34 states and 330 electoral votes.
Recommended Citation
Betapudi, Simeon A. and Betapudi, Hadassah, "The Wallet and The Gut: Forecasting the 2024 Presidential Election with a State-by-State Adaptation of the Time-for-Change Model" (2024). Science University Research Symposium (SURS). 219.
https://repository.belmont.edu/surs/219
