Forecasting U.S. State-Level Carbon Dioxide Emissions

Due to criticisms of potential identification issues within spatial panel data models, this study contributes to the literature by comparing forecasts of U.S. state-level carbon dioxide emissions against empirical reality using panel data models with and without spatial effects. From a policy standpoint, understanding how to predict emissions is important for designing climate change mitigation policies. From a statistical standpoint, it is important to test spatial econometrics models to see if they are a valid strategy to describe the underlying data. We find, unlike past studies, that non-spatial OLS estimators perform best in one to two-year-ahead forecasts, but the spatial panel data models perform better over a two to five year out-of-sample horizon