Arbitrage, Market Definition and Monitoring a Time Series Approach

Abstract

This article considers the application to regional price data of time series methods to test stationarity, multivariate cointegration and exogeneity. The discovery of stationary price differentials in a bivariate setting implies that the series are rendered stationary by capturing a common trend and we observe through this mechanism long-run arbitrage. This is indicative of a broader market definition and efficiency. The problem is considered in relation to more than 700 weekly data points on gasoline prices for three regions of the US and similarly calibrated simulated series. The discovery of a single common trend is consistent with competitive pricing and a broad market definition, but the finding of a single weakly exogenous variable affects this conclusion.

Extracting LonggRun Information from Energy Prices The Role of Exogeneity

“…The GC price is again the driver and is not impacted by the LA price in the longrun. This is consistent with the investigation of the trivariate system results in Burke and Hunter (2012) and Kurita (2008), but over a shorter time frame that excludes the 2008 financial markets crisis as is the observation that the GC price is WE. However, as the MW price is dependent on  .1 and  .5 , then it is appropriate to say that a linear relation between the LA and MW price is forced by the GC price and so in this case the MW and the LA are interdependent.…”

“…In this article we discuss further the developments in the literature previously summarized in Hendry and Juselius (2001), Hunter and Burke (2012), Hunter and Tabaghdehi (2013) among others. That information on price can be provided efficiently to customers and that consumers can monitor retail gasoline prices is one of the main concerns for the global economy.…”

“…As the largest movements relate to the earlier sample excluding the recent crisis, then it is anticipated the strongly persistent autoregressive behaviour during 2008 is indicative of the powerful movements that can be observed with series following stochastic trends. Burke and Hunter (2012) show that similar data can be readily calibrated and simulated as random walks. It should be noted that in the latter case the simulated data do not have any structural break, but vary in the same way as the actual data for the shorter sample used by Kurita.…”

“…We investigate long-run equilibrium in the US gasoline market using the error correction model. This case in particular is termed arbitrage correction by Burke and Hunter (2012). The hypothesis underlying this argument relates to the possibility that a sequence of regional gasoline prices that deviate from equilibrium give rise to an arbitrage opportunity that is correcting in the long-run.…”

“…Following, Johansen (1992), Hunter and Simpson (1995), Bauwens and Hunter (2000), and Burke and Hunter (2012) weak exogeneity in the long-run has been identified by imposing a restriction on a each row vector α i. =[0, 0, 0, 0, 0] from α in turn (for i=1, … ,8) and that excludes the long-run from each equation in the system.…”