Changes in the global oil market

Abstract

Using a new iterative algorithm that tests for possible breaks in the coefficients and residual variances of recursively identified structural equations, we examine changes in the parameters of the oil market model of Kilian (2009). Our analysis reveals breaks in the coefficients of the oil production and price equations, together with volatility shifts in all equations. In particular, the medium term response of production to aggregate demand shocks increases after 1980 and the price response to supply shocks is more persistent from the mid-1990s.All variables evidence changes in the relative contributions of individual shocks to their forecast error variances.JEL classification: E42, Q43.

Is the recent low oil price attributable to the shale revolution?

“…The econometric methodology used in this study builds on that of Bataa, Izzeldin, and Osborn (2016). A critical difference is that we have put the growth rate of U.S. oil production in the first place of the SVAR.…”

“…Fourth, although the growth rate of the real oil price shows one break in the seasonality component and two volatility breaks as in Bataa et al (2016), the seasonality is statistically significant only after the temporary OPEC collapse in 1985.…”

“…As in Bataa et al (2016) we conduct structural break tests for the above-mentioned SHVAR, equation-wise. Pagan and Robertson (1998) 0Σ (Â 0 ) −1 =Ω, whereΩ is the reduced-form VAR variance-covariance matrix.…”

An analysis of the global oil market using SVARMA models

“…This implies, the conventional VAR tools of impulse response analysis and forecast error variance decompositions can be misleading if constant parameters are assumed throughout the samples. Bataa et al (2016) carried out various sub-sample analysis of the oil market and found the parameters of oil market variables are subject to change over different time periods.…”

Changes in the relationship between short‐term interest rate, inflation and growth: evidence from the UK, 1820–2014

“…This paper implements the methods of Bataa et al (2013Bataa et al ( , 2018 which extends the above literature in a number of important ways. As emphasized in Bataa, Izzeldin, and Osborn (2016), our formal structural break analysis provides complementary information to TVP-VAR studies, allowing for discrete breaks of unknown number and, in particular, permitting the null hypothesis of no change to be explicitly considered. A discrete break test of the type that we use is known to have power against other alternatives, such as one in which the coefficients follow a random walk (see Stock &Watson, 1998 andBoivin &Giannoni, 2006).…”