Mean Reversion Techniques

Apologies for the long absence from blogging. I’ve spent the last week moving everything I’ve owned for the past 3 years to Singapore, and I’m still suffering from jetlag – hence my blogging at this ridiculously early hour.

Just before I left the United States, I purchased a book by Larry Connors after reading one of his articles on his proprietary Double 7s Strategy in an issue of Stocks and Commodities. The book, Short Term Trading Strategies That Work, includes a number of high-probability strategies that relate to stocks and ETFs. From what I gather, the underlying philosophies are:

1) Trade in the direction of the long-term trend.

2) Stocks and ETFs are mean-reverting.

3) Stops hurt the performance of a mean-reversion strategy.

He claims that his strategies are backed up by rigorous statistical testing, and includes a number of statistics to demonstrate the robustness of his strategies. He seems to focus mainly on hitting high-probability trades. However, after running a few tests of my own, I’ve discovered that:

1) These strategies work wonderfully with most stock indices, but strangely not for futures, forex, interest rates, and commodities. I’m hypothesizing that perhaps equities are truly mean-reverting, while other securities seem to be subject to large, defined trends. I didn’t have any ETF data to test his strategies on, but I suppose that his strategies would have worked well on them as well.

2) The parameters given are not always ideal – they can sometimes generate a high percentage of “right” trades, but the drawdown of any one single trade could possibly be fairly large – something most traders might not be comfortable trading. This also results in a relatively poorer Net Profit/Max Drawdown ratio.

3) In contrast to Mr Connors, I still believe that stops improve performance. To test this, I included some stops and re-optimized the parameters using both in and out-sample periods. To my delight, stops dramatically improved the Profit/Drawdown ratio, and sometimes even increased gross profit. The only trade off was that it lowered the probability of right trades. Even then, the percentage remained relatively high (> 50%)

This might be a good, diversified technique to trade equities with, given that my other trend-following strategies do not seem to work very well in this one area.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s