How can I tell if my system is ROBUST

Quote from Baruch:

... Why should RSI make money?

I'm not saying RSI should make money. Aafwintb asked a question about the 'robustness' of systems and, as an example, said should he use an RSI of 6 with x statistics or an RSI of 12 with y statistics. My comment was that choosing between 6 or 12 is not the most important thing. When looking for a 'robust' system you need to ensure that a wide range of input values are profitable i.e. 1-30 not just 6 and 12. In that way as the market changes in the future you are still likely to make money. You can replace RSI with anything.
 
Aafwintb,

Ryan Jones' book 'The Trading Game' has a couple of very good chapters on Optimization and Robust Statistics. The book is actually about money management so you probably wouldn't want to buy it just for those chapters.

Cheers
 
Quote from mmillar:

I'm not saying RSI should make money. Aafwintb asked a question about the 'robustness' of systems and, as an example, said should he use an RSI of 6 with x statistics or an RSI of 12 with y statistics. My comment was that choosing between 6 or 12 is not the most important thing. When looking for a 'robust' system you need to ensure that a wide range of input values are profitable i.e. 1-30 not just 6 and 12. In that way as the market changes in the future you are still likely to make money. You can replace RSI with anything.

OK
 
Quote from progers82:

ive been a system trader for over 6 years and in designing my systems i look for three financial figures
1)percentage win loss
2)profit ratio
3)ratio of win to loss.
I multiply all three together and if that equels 1 or larger then I go on. I have to have over 450 trades in my population or I wont consider the population large enough.
I then consider the sharp ratio and I consider the yearly return vs the largest drawdown. I I look to see if the annual returns are increasing or decreasing as time goes on.
I will not optimize my variables often at the most twice a year. Im always looking at the largest drawdown and challenging whether i can live with that drawdown.


Why do use the product of these three ratios, what does it mean, what does it express? Why do you consider 1 to be a cut-off level for this product?? What would be the value of this product for an "exceptioanlly good sytem;' in your estimation?
 
imo it means you have a good positive expectation and you won't be eaten alive by commissions and slippage. when you start getting below 1, on paper you might be profitable but in real live trading, unexpected events like slippage could hurt you.
 
Quote from progers82:
ive been a system trader for over 6 years and in designing my systems i look for three financial figures
1)percentage win loss
2)profit ratio
3)ratio of win to loss.
I multiply all three together...

Isn't "percentage win/loss" essentially the same as "ratio win/loss"??

Seems like you only need to know that ($win/$loss)*(#win/#loss) is > 1
 
if you were just using those two, then i would want my result to be much higher that 1 say in the 2+ range. I use all three and I use the 1 because when I am developing a trading system, it is so easy to be conned into believing something will work and most of the time it won't work into the future.
 
Quote from progers82:

if you were just using those two, then i would want my result to be much higher that 1 say in the 2+ range. I use all three and I use the 1 because when I am developing a trading system, it is so easy to be conned into believing something will work and most of the time it won't work into the future.

For clarity which two are you referring to PF & % Profitable OR % Proftable and Avg win/Avg Loss OR PF and Avg Win/Avg Loss?
 
Back
Top