How long need to i backtest an online daytrading system

For how long must I backtest an online daytrading system?

I am regularly asked how long one ought to backtest an on-line daytrading system. Though there's no very easy answer, I will certainly supply you with some guidelines. There are alex wilcox dallas a few variables that you need to consider when determining the duration for backtesting your online daytrading system:

Trade frequencyHow lots of professions daily does your daytrading system generate? It's trivial how long you backtest a daytrading system; it is necessary that you obtain adequate trades to make statistically valid presumptions *: If your online daytrading system produces three professions daily, i.e. 600 trades per year, then a year of testing gives you sufficient data to make trusted presumptions *. Yet if your trading system creates only three trades per month, i.e. 36 trades annually, then you need to backtest a couple of years to get trustworthy data. Underlying contractYou should take into consideration the features of the underlying contract. The graph below programs the average daily volume of the e-mini S&P: It does not make good sense to backtest a trading system for the e-mini S&P before 1999, since the contract merely didn't exist! In my viewpoint it does not make good sense to backtest an e-mini trading system prior to 2002 since at that time the market was entirely various; much less liquidity and various market individuals. I think that a trustworthy screening period for the e-mini S&P are the years 2002-- 2004.