Cointegration, Error Correction, and Price Discovery on Informationally Linked Security Markets

Using synchronous transactions data for IBM from the New York, Pacific and Midwest Stock Exchanges, we estimate an error correction model to investigate whether each of the exchanges is contributing to price discovery. Johansen's multi-variate cointegration test yields two cointegrating vectors which together verify the expected long-run equilibrium of equal prices across the three exchanges. Price discovery in our sense then refers to the adjustment process by which informationally linked security markets resolve price disparities after coincident but unequal price changes. Two error correction terms specified as the difference between IBM prices on the Pacific versus NYSE and on the Midwest versus NYSE indicate that adjustments maintaining the long-run cointegration equilibrium take place on all three exchanges. That is, IBM prices on the NYSE adjust toward IBM prices on the Midwest and Pacific Exchanges, just as Midwest and Pacific prices adjust to the NYSE. The findings are robust to several data collection procedures yielding different observation intervals, different orderings of the data tuples, and different time periods