LOL... 46.54% Annual Return... Max Drawdown 1.4%... ... So what's really your point in asking this... It's not for sale... But here's one interesting statistics... I tested a bunch of optimizable systems starting with specific but robust non-linear criteria included under 5 min. bar, closing the position at the end of the day... Total number of tests were: 124416 Out of 124416 systems in 3 years of testing data: 1848 were profitable (1.4%) Take the 1848 and put that in 5 years of ES with Sharpe Ratio of over 1.0 (unfortunately that the max number of years I have in ES data):136 (7.3% of 1848) Put that into 1987-current SP data: 26 systems with Sharpe Ratio over 1.0 (19% from 5 years) Out of all the tests... I only got 3 systems with Sharpe Ratio above 1.5 and annual return of over 30%.
Will write up a doc file in addition to the Ensign template over this weekend. I have got way too many pm's on that so I think I should just post the system on ET rather than sending everyone the template. Sashe
GANN, U forgot to add something. You're results or strategy is tested on 1 contract and don't have money management included. If you add MM you can boost that performance higher. Well... I can't believe you're sharing some info. It doesn't help u by sharing. No $$$$$$ = No Info. trend
Thanks Gann, Just comparing notes. My system is tested on all liquid futures back to 1990. S&P back to 1983. Intraday only down to 1 minute. No overnight risk. With money management I get a return of 50% plus. However my max dd will be something like 10-25% if past history is a guide. I asked about the +2 PF as I know from trading this system how demoralising it is trading sub 2's ! I don't think this is possible to a retail trader over a statistically valid number of intraday trades, though. By the way how did your system(s) perform around '93-'94 on the S&P? And also the first six months of 1988? For me they were two completetly different times but both annoyingly lean nevertheless.
Yes, my info is not worth much $$$$$... I'm just saying only 3 out of 124416 systems actually work in the long run. I don't think a lot of people in ET has done a rigorous test that I have and the conclusions from the statistics and patterns of what kind of systems work can only be known to the ones who have done it. I don't plan on giving that out. Even if they did the same tests or same kind of tests, they won't get the same conclusion as I have. So the statistics and the fact that I went through the test is worthless to others.... But one thing I can say is to be skeptical about the system the trader trades right now. I am sure there will be a time when the system starts to deteriorate. Same goes with the 3 systems I derived from the tests. I'm sure if I had 20 years of data, none or if I'm lucky 1 would survive...
Interesting point ... How do you monitor your systems ? Do you perform some sort of hypothesis tests and e.g. stop trading a system when the real DD reaches the 5% error zone ? Dierk Droth
Actually, I don't put weigh on the equity curve but look at the market condition to figure that out. Just because I did some optimization, it doesn't mean I don't understand the system. For all the systems I trade, I have a detailed understanding of, even though it's opinionated, when, how, and why it works. When any of the conditions that require for the market to have, changes, I'll be skeptical. Eventually, we trade the market, not the system... something a system trader forgets time to time.
Dierk, did you see my CBOT online seminar? (It is archived at http://www.cbot.com/cbot/dow/cont_detail/0,2614,4+9029,00.html). Doing a Monte Carlo simulation and then a hypothesis test to monitor a strategy was one of the topics I covered. It's nice to see someone else taking a rigorous quantitative approach to system monitoring.
Yeah I did and was quite impressed. It's seems to be a quite intriguing concept to me, so I put the above question here to see if there are some experiences from others. I appretiated your seminar a lot. Dierk