Modeling the presidential approval ratings of the United States using machine-learning : does climate policy uncertainty matter?

Abstract

In the wake of a massive thrust on designing policies to tackle climate change, we study the role of climate policy uncertainty in impacting the presidential approval ratings of the United States (US). We control for other policy related uncertainties and geopolitical risks, over and above macroeconomic and financial predictors used in earlier literature on drivers of approval ratings of the US president. Because we study as many as 19 determinants, and nonlinearity is a well-established observation in this area of research, we utilize random forests, a machine-learning approach, to derive our results over the monthly period of 1987:04 to 2023:12. We find that, though the association of the presidential approval ratings with climate policy uncertainty is moderately negative and nonlinear, this type of uncertainty is in fact relatively more important than other measures of policy-related uncertainties, as well as many of the widely-used macroeconomic and financial indicators associated with presidential approval. More importantly, we also show that the importance of climate policy uncertainty for the approval ratings of the US president has grown in recent years.