Steel consumption and economic activity in the UK: The integration and cointegration debate

Abstract

This research examines whether a long-run stationary equilibrium relationship holds between economic activity and the consumption of crude steel within the UK. Using the theory of fractionally integrated and cointegrated processes, and allowing for the possibility that the equilibrium path changes abruptly at occasional points in time, it is possible to determine if steel consumption and economic activity follow a common stochastic trend or whether the two series randomly drift apart over time. Evidence is found to support such a long term relationship. This result is at odds with the conclusions drawn by previous researchers in the area. The reason for this difference may be due to these researchers concentrating only on I(0) and I(1) specifications, without consideration of fractional possibilities and also to a failure to account for structural breaks in the equilibrium relationship. Such conclusions are made within the framework of the ARFIMA methodology that yields reliable inferences on the degree of fractional integration and cointegration. Critical values for fractional contegration with an ARFIMA model in the presence of structural breaks are also derived in this paper.