We study the relationship between energy consumption and real GDP in the USA using a multivariate time-varying model [1973Q1–2014Q1]. We show that the combination of disaggregation into specific fuels and time variation gives more nuanced results than the alternatives for the USA. Specifically, we find that the Granger causal relationship between total energy and real US GDP is bi-directional through much of the 1990s, but unidirectional running from real US GDP to energy consumption in the 2000s. As for each fuel, similar patterns of change were observed in the causal relationship between coal consumption and real US GDP. Oil consumption largely shows a bi-directional relationship between consumption and US GDP, especially after 2009. And natural gas consumption shows a brief period in the early-to-mid 2000s where US GDP predicts energy consumption, but primarily shows that natural gas consumption and economic growth are independent.