Transfer Learning for Spatial Autoregressive Models with Application to U.S. Presidential Election Prediction
This work addresses the challenge of limited spatial data for election prediction in swing states, representing an incremental advancement in spatial econometrics.
The authors tackled the problem of predicting U.S. presidential election results with spatially dependent data and small sample sizes by proposing a transfer learning framework called tranSAR within the SAR model, which improved estimation accuracy and outperformed traditional methods in predicting swing state outcomes, including forecasting a Democratic win in 2024.
It is important to incorporate spatial geographic information into U.S. presidential election analysis, especially for swing states. The state-level analysis also faces significant challenges of limited spatial data availability. To address the challenges of spatial dependence and small sample sizes in predicting U.S. presidential election results using spatially dependent data, we propose a novel transfer learning framework within the SAR model, called as tranSAR. Classical SAR model estimation often loses accuracy with small target data samples. Our framework enhances estimation and prediction by leveraging information from similar source data. We introduce a two-stage algorithm, consisting of a transferring stage and a debiasing stage, to estimate parameters and establish theoretical convergence rates for the estimators. Additionally, if the informative source data are unknown, we propose a transferable source detection algorithm using spatial residual bootstrap to maintain spatial dependence and derive its detection consistency. Simulation studies show our algorithm substantially improves the classical two-stage least squares estimator. We demonstrate our method's effectiveness in predicting outcomes in U.S. presidential swing states, where it outperforms traditional methods. In addition, our tranSAR model predicts that the Democratic party will win the 2024 U.S. presidential election.