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.