Discussing the article: "Statistical Arbitrage Through Cointegrated Stocks (Part 1): Engle-Granger and Johansen Cointegration Tests"
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Check out the new article: Statistical Arbitrage Through Cointegrated Stocks (Part 1): Engle-Granger and Johansen Cointegration Tests.
This article aims to provide a trader-friendly, gentle introduction to the most common cointegration tests, along with a simple guide to understanding their results. The Engle-Granger and Johansen cointegration tests can reveal statistically significant pairs or groups of assets that share long-term dynamics. The Johansen test is especially useful for portfolios with three or more assets, as it calculates the strength of cointegrating vectors all at once.
Recently, my partner and I were in an informal meeting with a trader who is used to operating dollar contracts on the Brazilian Exchange B3. She said she would love to have the resources to try “some kind of stat arb on agricultural commodities”, but being a traditional discretionary trader trained in technical analysis and price action, without a strong background in math or statistics, she was positive in saying that statistical arbitrage would be “out of her reach”. She was echoing that well-known belief we talked about at the beginning, the belief that statistical arbitrage is not within the reach of the retail trader.
To make a long story short, and go right to what you are looking for here, we then turn that into a challenge among friends: what if we used our free time to develop an automated statistical arbitrage framework for learning purposes? But how to do that if none of us is a great statistician, mathematician, or has the computational power required to beat the big players? We did what learners usually do: we started doing academic research to understand the problem, the alternatives already found in the market, studying the successes, but also the failures.
Our first baby steps resulted in an article I published here recently about the mathematician and hedge fund manager Jim Simons and his legendary Medallion fund. In that article, we used a barebones EA to illustrate statistical arbitrage between XAUEUR and XAUUSD.
The graph below shows our backtest results previously published here.
Author: Jocimar Lopes