Suppose one could find a stock whose price (or log-price) series was stationary and therefore mean-reverting. This would be a wonderful investment opportunity. Whenever the price was below the mean, one could buy the stock and realize a profit when the price returned to the mean. Similarly, one could realize profits by selling short whenever the price was above the mean. Alas, returns are stationary but not prices. We have seen that log-prices are integrated. However, not all is lost. Sometimes one can find two or more assets with prices so closely connected that a linear combination of their prices is stationary. Then, a portfolio with weights assigned by the cointegrating vector, which is the vector of coefficients of this linear combination, will have a stationary price. Cointegration analysis is a means for finding cointegration vectors.
KeywordsTrading Strategy Hedge Fund Statistical Arbitrage Vector Error Correction Model Closing Price
- Alexander, C. (2001) Market Models: A Guide to Financial Data Analysis, Wiley, Chichester.Google Scholar
- Alexander, C., Giblin, I., and Weddington, W. III (2001) Cointegration and Asset Allocation: A New Hedge Fund, ISMA Discussion Centre Discussion Papers in Finance 2001–2003.Google Scholar
- Enders, W. (2004) Applied Econometric Time Series, 2nd ed., Wiley, New York.Google Scholar
- Pole, A. (2007) Statistical Arbitrage, Wiley, Hoboken, NJ.Google Scholar
- Vidyamurthy, G. (2004) Pairs Trading, Wiley, Hoboken, NJ.Google Scholar