If there is a quantitative measure for Edge, what is it?

You need a collection of trade results, the more the better. If backtested numbers are used make sure realistic transaction costs (slippage & commission) are reflected. Calculate mathematical expectancy. Plot mathematical expectancy as a time series. Evaluate the downside volatility of this time series. An "overall" positive expectancy is worth little if it has severe downside potential that persists long enough to take your account to zero; even if this is infrequent.

If this time series is relatively stable, and positive, and based on reasonable inputs, and it exceeds the mathematical expectancy of your appropriate benchmark, then you probably have an edge.

Check the skew of your trade results. If it is heavy to the left you may have a problem with your risk managment (effectiveness of your stops).
 
Quote from Equalizer:

I believe that you are asking the following: "Are my results (backtested or otherwise) statistically significant?"

i.e. you are trying to ascertain that your out-of-sample good (I hope - and by whatever measure you define good) results have a high probability of not being attributed to chance alone.

Do a search on the web about statistical inference, hypothesis testing etc. Depends on your current stats knowledge.

If memory serves, Aaron Schindler did a web presentation (CME, or CBOT?) a while back where he presents a trivial system and touches on the subject - that might be of some help if this subject is new to you. It is rather simplistic though - but a start nonetheless.

[Edit] Found it:
http://www.cbot.com/cbot/pub/cont_detail/0,3206,929+15785,00.html

Can't remember how relevant it is...

Then again, there is no guarantee. Spurious relationships exist - it can be extremely difficult to distinguish causal relationships (particularly ephemeral ones) from spurious ones.
More...

Q

http://www.cbot.com/cbot/pub/page/0,3181,1070,00.html

Strategies

* Using Volume at Price to Trade Gold
05.25.2006

...

* Buying and Selling the Market with Long and Short Futures
08.23.2000

UQ

Obviously there are so many potentially profitable strategies available there, plus some known methodlogies including your suggestion that can be used to validate individual system's statistical significancy. So everyone should make profits easily, small or large.

Supposing all of them are having positive expectancy, then can we say each one of them is having an Edge by itself individually?

Should we add large capital more than 20 times of initial capital to trade them without ceasing, regardless of actual drawdown %?

Perhaps an Edge should be measured by a set (minimum nember) of measures, instead of just one single measure.
 
Quote from ecritt:

You need a collection of trade results, the more the better. If backtested numbers are used make sure realistic transaction costs (slippage & commission) are reflected. Calculate mathematical expectancy. Plot mathematical expectancy as a time series. Evaluate the downside volatility of this time series. An "overall" positive expectancy is worth little if it has severe downside potential that persists long enough to take your account to zero; even if this is infrequent.

If this time series is relatively stable, and positive, and based on reasonable inputs, and it exceeds the mathematical expectancy of your appropriate benchmark, then you probably have an edge.

Check the skew of your trade results. If it is heavy to the left you may have a problem with your risk managment (effectiveness of your stops).
More...

Personally I like this approach and I think that could be practical, useful and helpful to find and (I think, indirectly) define an edge which has been discussed on ET so many times so far.

Adding significantly more capital on top of an initial one would be relatively safe and feasible by this approach, I would guess. Many thanks.
 
Quote from OddTrader:

Q

http://www.cbot.com/cbot/pub/page/0,3181,1070,00.html

Strategies

* Using Volume at Price to Trade Gold
05.25.2006

...

* Buying and Selling the Market with Long and Short Futures
08.23.2000

UQ

Obviously there are so many potentially profitable strategies available there, plus some known methodologies including your suggestion that can be used to validate individual system's statistical significancy. So everyone should make profits easily, small or large.

Supposing all of them are having positive expectancy, then can we say each one of them is having an Edge by itself individually?

Should we add large capital more than 20 times of initial capital to trade them without ceasing, regardless of actual drawdown %?

Perhaps an Edge should be measured by a set (minimum nember) of measures, instead of just one single measure.
More...
Emm..., not quite, you'll find that many of these publicly available "potentially profitable" strategies/methods presented fail miserably under the cold harsh scrutiny of backtesting. If you add a discretionary dimension then you change it completely. So then next question is usually why can't you simply tell a computer what it is that you do? The answer is that it is extremely difficult to do that - for numerous reasons. Then again computers can do things that are incredibly difficult for human trader to do.

Regardless of the approach, what you are trying to determine is whether your profitability is based purely on chance alone - which is what my post was alluding to. For a simplistic example, if you have a collection of 100 trades, and 95 were loses, but the 5 winners were huge, then do you have an edge? Can you trade this way?

Once you have a profitable method that you have verified is statistically significant based on your measurements - then you can begin to discuss various measures as you point out.

What these are would be dependent on your approach in addition to your own personal utility. How much of a drawdown can you tolerate? What level of risk is acceptable to you (and of course how do you define and measure risk)? How many consecutive losses can you handle before you are "psyched-out". Sharpe ratio? Sortino ratio? How do you know if the edge has disappeared, or the string of losses was simply due to pure chance? Annual return? etc... The list goes on.

You might wish to search for some of acrary's posts.
 
Quote from ecritt:

You need a collection of trade results, the more the better. If backtested numbers are used make sure realistic transaction costs (slippage & commission) are reflected. Calculate mathematical expectancy. Plot mathematical expectancy as a time series. Evaluate the downside volatility of this time series. An "overall" positive expectancy is worth little if it has severe downside potential that persists long enough to take your account to zero; even if this is infrequent.

If this time series is relatively stable, and positive, and based on reasonable inputs, and it exceeds the mathematical expectancy of your appropriate benchmark, then you probably have an edge.

Check the skew of your trade results. If it is heavy to the left you may have a problem with your risk managment (effectiveness of your stops).
More...
Good post.
 
Quote from Equalizer:


Regardless of the approach, what you are trying to determine is whether your profitability is based purely on chance alone - which is what my post was alluding to.
More...

Probably that would be the right direction to define an edge quantitatively. Thanks.
 
Q

"Do Domestic Investors Have an Edge?"
http://www.nber.org/papers/W10502

---- Abstract -----

We investigate whether domestic investors have an edge over foreign investors in trading domestic stocks.Using Korean data, we show that foreign money managers pay more than domestic money managers when they buy and receive less when they sell for medium and large trades. The sample average daily trade-weighted disadvantage of foreign money managers is of 21 basis points for purchases and 16 basis points for sales. There is also some evidence that domestic individual investors have an edge over foreign investors. The explanation for these results is that prices move more against foreign investors than against domestic investors before trades.

UQ
 
Quote from OddTrader:

Q

"Do Domestic Investors Have an Edge?"
http://www.nber.org/papers/W10502

---- Abstract -----

We investigate whether domestic investors have an edge over foreign investors in trading domestic stocks.Using Korean data, we show that foreign money managers pay more than domestic money managers when they buy and receive less when they sell for medium and large trades. The sample average daily trade-weighted disadvantage of foreign money managers is of 21 basis points for purchases and 16 basis points for sales. There is also some evidence that domestic individual investors have an edge over foreign investors. The explanation for these results is that prices move more against foreign investors than against domestic investors before trades.

UQ
More...

Hmmm...it's a small difference. Could it be due to transaction costs associated with the kind of broker that "foreign" investors have to use? I can't get into Korea using IB; would have to pay more through Goldman to get access. Maybe the local Koreans are paying discount rates and most foreigners are paying full service rates?
 
You must log in or register to reply here.
Back
Top