There seems to be a discrepency for the daily hi and low quotes of the INDU when you compare the day's quote and the historical data quote of Yahoo. The historical data gives a higher range. why is this? this is pretty bad for backtesting! notice: today's HL, regular quote http://finance.yahoo.com/q/bc?s=^DJI&t=5d 10,560.81 - 10,466.07 today's HL, historical quote http://finance.yahoo.com/q/hp?s=^DJI 10,589.92 - 10,438.36 that's a 57 point difference. why? thanks
Not necessarily. The point of backtesting is to test your system, not to test your data. Even if the historical data is flawed, you can still get a good idea of your system performance if you do a proper backtest. Of course you'll have to accept the fact of that particular data source being no good for actual trading.
The difference is caused by how todays data is calculated vs how the historical data is calculated. Its years since I played with yahoo data but I seem to recall that the historical data has wider tails than the daily data and this is caused by the way that the index component prices are added together. Print vs ???? comes to mind. I think the historical might be assuming that all the highs come at the same time and just adding them all together. If you wanted to backtest a strategy you can't base it on yahoo data, you need to use something thats actually tradable like EYM for futures or DIA for a basket.
kiwi, thanks for the insight. the strategy was based on the cash INDU. i suggest using the ^djx through yahoo if anyone needs cheap historical data for cash index without the extreme tails.
You can backtest a strategy on any data as long as you're not just seeking to curve-fit the data. The goal is to have a robust system: one that isn't just some ad hoc exploitation of a particular set of data. If your system can't trade in more than one timeframe, that's a good indication that you're probably not trading with a robust system.
I would hesitate to trade a market-specific strategy unless I backtested it completely and found it superior to the best general system I had available. Let me emphasize that I'm not saying robustness is preferred to actual winning results. Nothing succeeds like success.