Expectancy above .50??

[man]

totally agreed. use sharpe and you got what you want. use sortino if you want to be more aggressive. you can compare systems directly, no matter what their frequency is.

as for the tradestation graphics someone postes bevore. again a source of trouble. it does not show times of much are little activity. it is again not what you will finally "feel" ... the charts are misleading as is most TS output. nevertheless experienced people overcome this by learning how to read the TS output by combining different bits and pieces.

 

[nononsense]

Quote from man:

totally agreed. use sharpe and you got what you want. use sortino if you want to be more aggressive. you can compare systems directly, no matter what their frequency is.

[]

Let it be known that in the past some very smart people at ET have argued exactly the opposite: believing the Profit Ratio to be preferable to the Sharpe Ratio. (you could do a search)

As for myself, I find a quick look at my Profit Ratio useful, at my Sharpe Ratio less useful. I use in fact a much more sophisticated criterion that took me years to develop.

nononsense

 

[Walther]

Quote from shanoballs:

Here is another example. Now as discussed before, the previously shown results of strategies do not present what one would call tradable results. Here is another strategy that, based on the numbers, I would consider very tradable. The only downside is the number of trades in comparison to the previously shown strategies. It appears the less trades a strategy takes, the better its numbers look. Although these results are obtained using out of sample data, and includes slippage, my main concern with this setup is the statistical significance of data. So far for the forward tests it has been performing well. But can one really know when the window of stationarity for the strategy will shift? Or that it has shifted? Specially when using strategies that are based off of lengths? Any thoughts on this?

Thanks,

shane
It just depends on the system .Trend following system will not do well in range bound environment and vice versa. To solve this I use independent studies to determine what system( method ) to use for current conditions . I am afraid that there is no other way around it.

 

[man]

Quote from nononsense:

Let it be known that in the past some very smart people at ET have argued exactly the opposite: believing the Profit Ratio to be preferable to the Sharpe Ratio. (you could do a search)

did a (very quick) search, did not find confirmation of your statement. i personally found people on ET that did very well, yet ignored sharpe completely. but i found none who was familiar with the concept yet perceived it as of less value than profit factor.

actually i think one of the biggest flaws people suffer from is wrong utility function. i think it is great that you took time to develop it! though i admit i still do not honestly consider to change mine. reason for that is that i want to be match my personal utility function. i hate too much volatility. naturally i do not like it downside but i get concerned with too much upside as well. at the moment we do print much in trend following, but i prefer stable 2%- to 10%-months ... but that is just me ...

 

[nononsense]

Quote from man:

did a (very quick) search, did not find confirmation of your statement. i personally found people on ET that did very well, yet ignored sharpe completely. but i found none who was familiar with the concept yet perceived it as of less value than profit factor.

actually i think one of the biggest flaws people suffer from is wrong utility function. i think it is great that you took time to develop it! though i admit i still do not honestly consider to change mine. reason for that is that i want to be match my personal utility function. i hate too much volatility. naturally i do not like it downside but i get concerned with too much upside as well. at the moment we do print much in trend following, but i prefer stable 2%- to 10%-months ... but that is just me ...

man,

No arguing about this. You should use what works best for you.

FYI:

Quote from tntneo:

onelot is right, that's my definition of profit factor.

I also look at Sharpe ration nononsense btw.
which indeed takes into consideration the smoothness of equity curve.
I like Sharpe as high as possible obviously.

I admit using profit factor more easily, it talks more to traders while Sharpe talks more to investors
Both are fine by me.
yes, it's also true that Sharpe will also catch your drawdown while profit factor can't.

but like I said I usually focus heavily on profit factor, max drawdown and average drawdown, while number of trades is high enough to be statistically valid.

tntneo

 

[man]

traders think in dollars and pnl, fund managers think in % and equity curve figures. it is more about professional OPM managers than investor's point of view. 90% of investors do not know what to do with all these figures anyways ...

 

[Trader666]

Quote from man:

profit factor is a very flawed concept. it does not account for any smoothness of the equity curve. you could have a profit factor of 2.5 and still prefer a system that shows half of that. frequency of trading is the thing that is missing plus time, spells smothness calculated by standard deviation of returns

Totally disagree. If I were limited to one metric I would choose profit factor. It's elegant in its simplicity and tells you how much you can expect to gain for every dollar lost. For example, a PF of 1.84 means you can expect, on average, to gain $1.84 for every $1 lost. PF = Total Profit/Total loss. Another way of looking at is: (PW * AW) / (PL * AL), where PW = Probability of a win, AW = Average win, PL = Probability of a loss, and AL = Average loss.

There are very few systems with a PF of 1.25 that I'd prefer over one with 2.5. Things like the system with 2.5 making all of its gains from a single trade. But I can give you examples like this for ANY single metric. So of course it must be looked at in conjunction with other metrics.

Profit Factor is not an entire equity curve in a single number, but neither is Sharpe which really is flawed BTW, because it penalizes large positive returns.

 

[man]

Quote from Trader666:

Profit Factor is not an entire equity curve in a single number, but neither is Sharpe which really is flawed BTW, because it penalizes large positive returns.

well, sharpe tells much more about an equity curve than does profit factor. and if you don't want to penalize upward vola then
use sortino. nevertheless, profit factor IS flawed.

 

[science_trader]

Personally my sharpe ratio is 5.2 at the moment....and I am typically penalized by up vol... So it seems to be possible to reach something higher than 1.

 

[man]

Quote from science_trader:

Personally my sharpe ratio is 5.2 at the moment....and I am typically penalized by up vol... So it seems to be possible to reach something higher than 1.

if it is for longer than 2 years and we are not talking short any kind of option, then i'd say that 5.2 is a level where sortino and sharpe won't differ that much. high sharpes usually show low deviation in either direction.