Some traders asked me for how long one should backtest a trading system. There’s no easy answer, and there are a few factors that you need to consider when determining the period for backtesting your trading system.
It’s not important how long you backtest a trading system, it’s important that you receive enough trades to make statistically valid data. If your trading system generates 2 trades per day, or 300 trades per year, then a year of testing gives you enough data to make reliable decission. But if your trading system generates only 2 trades per month or 24 trades per year, then you should backtest a couple of years to receive reliable data.
It doesn’t make sense to backtest a trading system for the GBP/USD on an e-mini trading account before 2002 because at that time the market was completely different, less liquidity and different market participants. I believe that a reliable testing period for the e-mini between the years 2002 – 2008.
The bigger the sample data you get then the smaller from margin of error and then it will built more reliable data that needed to develop trading system. Ussually I’ll do a backtest for past two to four years ago then combining with 6 month of Forward test will give me confidence to use a new development system.
i also believe so that markets change when new participants emerged. like our malaysian cpo futures market, the market changed in year 2006/2007 when the global market was fueled with excessive liquidity. many systems that worked robustly before 2006 failed after 2006. thats why many times were said that risk management is the most important element in trading in case a system fails,we can still survive
ReplyDelete