Oil prices: Breaks and trends

This paper contributes to the literature of the stationarity of financial time series and the literature on oil and macroeconomics in several ways. First, it uses Kejriwal and Perron (2010) sequential procedure to endogenously determine multiple structural changes in real oil prices without facing the circular testing problem between structural changes and stationary assumptions of previous tests. Second, it performs a diagnostic check to detect the significance and magnitude of the potential breaks. Third, it uses the above information to test for the existence of stochastic trends in real oil prices, and fourth, it speculates about possible explanations for the break dates found in order to encourage further work and discussions. The exercise uses monthly data from January 1861 to August 2011.

► The model endogenously determine multiple structural changes in real oil prices. ► The methods used does not face the circular testing problem. ► It also detect the significance and magnitude of the breaks detected. ► It tests for the existence of stochastic trends. ► It explains the reasons for the break dates found.