[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: [amibroker] Understanding Portfolio Backtest Reports ..was..Re: PositionScore Ideas



PureBytes Links

Trading Reference Links









Hi Gary –

 

I agree with you.  

 

In my opinion, the name of the game is minimization
of drawdown first, maximization of return second.  Given a trading system
with a low drawdown, return can often be improved by using additional leverage
(margin, options, futures, etc) up to the point where drawdown is painful. 
Combining return with drawdown in a single metric is important.

 

I’ve been critical of Sharpe Ratio
for exactly the reason you state – that the Sharpe Ratio score for a
trading system drops if a small winning trade is replaced by a larger winning
trade.

 

It is possible to create a Sharpe
Ratio-like metric using the standard deviation of only the losing trades in the
denominator that does not penalize winning trades.  

 

I like the UPI metric.

 

Thanks,

Howard

 



-----Original Message-----
From: Gary A. Serkhoshian
[mailto:serkhoshian777@xxxxxxxxx] 
Sent: Sunday, December 14, 2003
11:52 AM
To: amibroker@xxxxxxxxxxxxxxx
Subject: Re: [amibroker]
Understanding Portfolio Backtest Reports ..was..Re: PositionScore Ideas

 



Phsst,





 





I'll just carry forward what others have shared, but I'd love to read
responses from Fred, Chuck, Howard, and Mark in terms of their opinions and
usage if they have the time/inclination.





 





The big headline to share is on Sharpe and UPI, IMHO.  Both
are risk-adjusted measures of the equity curve, but look at it from different
perspectives.  Sharpe penalizes both positive and negative volatility,
whereas UPI penalizes only negative volatility (i.e. drawdowns).  For this
reason, I choose to look at UPI becuase I personally don't mind positive
volatility (ie. big gains in short period of time).  CAR/MaxDD is a quick,
back of the envelope calculation that will get you in the same ballpark as UPI.





 





Also understand that money market will have the best (i.e.
infinity) Sharpe and UPI because you have no volatility in the equity
curve.  Of course, we are not interested 0.5% CAR so we cast aside
MM.  No guts, no glory.





 





Hope this helps,





Gary

Phsst
<phsst@xxxxxxxxx> wrote:





Chuck,<span
>

As you can see, I've changed the Subject because I
think we may have
an opportunity thru your questions to get better
insight into reported
figures on the backtester report.

If you reply, and I certainly hope that you do,
just drop your name
from the Subject.

You are right... there are some things very wrong
with the backtest
reports that I posted, and I had not noticed them
until you pointed
them out.


Specifically:

CR> 1.   Both of them show nice
annual returns (89-140%).

Annual returns this high should be treated with
suspicion and cause
the system developer to be extra vigilant in
analyzing the reported
figures. Unfortunately I failed to notice the
discrepancies that you
noted. You can bet that I'll be more vigilant in
the future, looking
specifically at those figures you zeroed in on.


CR> 2.   Yet, the average p/l is
negative (2-4%).

I thought I might have made a mistake
copying/pasting on this one, but
I have verified that the actual backtest report
contained these figures.

CR> 3.   The Sharpe ratio is
negative.

I have to plead ignorance here. I've read as much
as is available in
the documentation relating to the Sharpe ratio
(among others). But
when I am unable to get a clear idea of exactly
how to interpret some
of these metrics then I tend to just ignore them
on the backtest report. 

I would really like to see a dialog on this forum
related to the real
value of Sharpe, Ulcer, etc.

CR> 4.   The average win is 3%.

Same response as #2.

CR> 5.   The average loss is 10-11%.

Same response as #2.

CR> What's the story???

Good question Chuck.

In addition to posting this response, I'll send TJ
the actual backtest
report(s) to see if there is a rational
explanation for the reported
figures which he could post here, or if it is a
genuine bug.

If TJ needs the code, I'll be glad to send it to
him.

If there is a problem with my backtest AFL code,
then I'd want to
understand what coding conditions could cause
this.

Anyway, thanks for taking a critical look at the
figures.

Do you suppose that you and others who have good
insight into the
reported metrics could help the rest of us better
understand how to
interpret the last eleven (11) reported figures on
the Backtest Report?

Regards,

Phsst

--- In amibroker@xxxxxxxxxxxxxxx, "Chuck
Rademacher"
<chuck_rademacher@x> wrote:
> Phsst,
> 
> There seems to be something radically wrong
with your stats (below):
> 
> 1.   Both of them show nice annual
returns (89-140%).
> 
> 2.   Yet, the average p/l is
negative (2-4%).
> 
> 3.   The Sharpe ratio is negative.
> 
> 4.   The average win is 3%.
> 
> 5.   The average loss is 10-11%.
> 
> What's the story???
>   -----Original Message-----
>   From: Phsst [mailto:phsst@xxxx]
>   Sent: Saturday, December 13, 2003
5:31 PM
>   To: amibroker@xxxxxxxxxxxxxxx
>   Subject: [amibroker] Re:
PositionScore Ideas
> 
> 
>   Greg,
> 
>   This backtest comparison is for
illustrative purposes only. I make no
>   claims regarding these test
results other than the AFL and Setup
>   criteria was identical for both
tests. The only difference was the
>   assignment of PositionScore = QRS
versus PositionScore = RSW.
> 
>   NOTE:
> 
>   // RSW = .4*(Total Return
13-Week)+.3*(Total Return 26-Week)+.3*(Total
>   Return 1-Year)
>   tr13 = 0.4 * (C - Ref(C, -65)) /
Ref(C, -65) * 100;
>   tr26 = 0.3 * (C - Ref(C, -130)) /
Ref(C, -130) * 100;
>   tr52 = 0.3 * (C - Ref(C, -260)) /
Ref(C, -260) * 100;
>   RSW = tr13 + tr26 + tr52;
>   PositionScore = RSW;
> 
>   Date Range 6/1/1995 to Present
(No QRS scores exist prior to this)
> 
>   Direct comparison:
> 
>        
RSW SCORE            QRS
SCORE
>        
Long trades           
Long trades
>   Initial
capital     
100000            100000
>   Ending
capital      22984180     
190338380
>   Net
Profit      22884180     
190238380
>   Net Profit
%      22884.18%     
190238.38%
>   Exposure
%     
94.25%            94.16%
>   Net RAR
%      24280.98%     
202035.63%
>   Annual Return
%     
89.07%             
142.19%
>   Risk Adj Retn
%     
94.50%           
151.01%
> 
>   All
trades      7431 (100.00
%)      7487 (100.00 %)
>   Avg.
Profit/Loss      3079.56 25409.16
>   Avg. Profit/Loss
%      -4.16%      -2.88%
>   Avg. Bars
Held              
2.65      2.63
> 
>  
Winners              
3829 (51.53 %)      4066 (54.31 %)
>   Total
Profit      64437022.92     
436648089.7
>   Avg.
Profit      16828.68     
107390.09
>   Avg. Profit
%     
3.10%            3.13%
>   Avg. Bars
Held     
2.33            2.33
>   Max.
Consecutive      17      17
>   Largest
win      978262.15     
7798920.06
>   # bars in largest
win      2      2
> 
>  
Losers      3602 (48.47
%)            3421
(45.69 %)
>   Total
Loss      -41552842.92     
-246409709.4
>   Avg.
Loss      -11536.05     
-72028.56
>   Avg. Loss
%     
-11.88%           
-10.03%
>   Avg. Bars
Held      2.98           
2.99
>   Max.
Consecutive      13      12
>   Largest
loss     
-542767           
-4301835.5
>   # bars in largest
loss      6      6
> 
>   Max. trade
drawdown      -610851.92     
-4864832.72
>   Max. trade %
drawdown     
-98.69%           
-99.67%
>   Max. system
drawdown     
-2119041.36      -15587244.83
>   Max. system %
drawdown     
-34.68%           
-27.63%
>   Recovery
Factor     
10.8            12.2
>  
CAR/MaxDD     
2.57            5.15
>  
RAR/MaxDD     
2.72            5.46
>   Profit
Factor     
1.55            1.77
>   Payoff
Ratio     
1.46            1.49
>   Standard
Error      2982472.3     
25676798.01
>   Risk-Reward
Ratio      0.44      0.38
>   Ulcer
Index     
12.1            7.64
>   Ulcer Performance
Index      6.92      17.9
>   Sharpe Ratio of
trades      -0.72      -0.86
>  
K-Ratio                      
1.09      0.93
> 
>   FWIW, I have some other systems /
variations that I'll run a RSW vs.
>   QRS comparison on. If there are
any notable improvements to the RSW
>   results, I'll post them.
> 
>   Regards,
> 
>   Phsst
> 
>   --- In amibroker@xxxxxxxxxxxxxxx,
"Greg" <gregbean@xxxx> wrote:
>   > Phsst,
>   >
>   > Yes I think it is (Total
Return 13-Week) means (Pct Price gain in
>   > 13-Weeks). The terms are
from ValueLine, I think.
>   > <a
href="">http://www.valueline.com/
>   >
>   > IBD definition of Relative
Strength:
>   >
>   >  Relative Price
Strength (RS) Rating or Relative StrengthThis IBD
>   SmartSelect® Corporate Rating
measures each stock's price performance
>   over the latest twelve months
compared to all other stocks. The rating
>   scale ranges from 1 (lowest) to
99 (highest). Stocks rating below 70
>   indicate weaker or more laggard
relative price performance.
>   > <a
href="">http://www.investors.com/
>   >
>   >
>   > Greg
>   >
>   >   ----- Original
Message -----
>   >   From: Phsst
>   >   To:
amibroker@xxxxxxxxxxxxxxx
>   >   Sent: Saturday,
December 13, 2003 4:52 PM
>   >   Subject:
[amibroker] Re: PositionScore Ideas
>   >
>   >
>   >   Greg,
>   >
>   >   I'll be happy to
do a comparison on just about anything that
might be
>   >   comparable to
IDB's RS Rank.
>   >
>   >   I assume that
(Total Return 13-Week) means (Pct Price gain in
>   >   13-Weeks), and
so on?
>   >
>   >   Worth noting
here, that IDB's RS Rank is a score between 1 and 100
>   >   that ranks each
particular stock against the whole mkt for the
>   past year.
>   >
>   >   But for
positionscore pusposes, we are not limited to a score
of 1 -
>   >   100, so I can do
the raw comparison of results from your formula
>   to QRS.
>   >
>   >   I'll post back
later under this same Subject.
>   >
>   >   Regards
>   >
>   >   Phsst
>   >
>   >
>   >   --- In
amibroker@xxxxxxxxxxxxxxx, "Greg" <gregbean@xxxx> wrote:
>   >   > Hi Phsst.
>   >   >
>   >   > Here is a
formula that I have been told closely follows that
of IBD.
>   >   Could you please
do the comparison you offered ?
>   >   >
>   >   > RSW =
.4*(Total Return 13-Week)+.3*(Total Return
26-Week)+.3*(Total
>   >   Return 1-Year)
>   >   >
>   >   > Thanks,
>   >   > Greg
>   >   >  
----- Original Message -----
>   >   >  
From: Phsst
>   >   >  
To: amibroker@xxxxxxxxxxxxxxx
>   >   >  
Sent: Saturday, December 13, 2003 1:26 PM
>   >   >  
Subject: [amibroker] Re: PositionScore Ideas
>   >   >
>   >   >
>   >   >  
Al,
>   >   >
>   >   >  
My favorite is the QP2 QRS value (GetExtraData("QRS"). The
QP2 QRS
>   >   >  
value is supposed to be a 'knockoff' of the IBD RS ranking
score.
>   >   >
>   >   >  
I almost always get a significant boost using this ranking
>   figure as
>   >   >  
as the positionscore.
>   >   >
>   >   >  
If you do not have QP2, but have any ideas about how to do
>   your own RS
>   >   >  
Rank calculation, I'd be happy to run some comparisons for
you (or
>   >   >  
anyone else) to measure your calculated RS Rank against
QP2's QRS
>   >   rank.
>   >   >
>   >   >  
Cheers,
>   >   >
>   >   >  
Phsst
>   >   >  
--- In amibroker@xxxxxxxxxxxxxxx, "Al Venosa" <advenosa@xxxx>
>   wrote:
>   >   >  
> Hi, all:
>   >   >  
>
>   >   >  
> I've been experimenting with variuos short term trading
systems
>   >   >  
lately (average trade durations of about 2.5 days), and I was
>   looking
>   >   >  
for ideas on how best to rank a watchlist to get the best
>   candidates
>   >   >  
for portfolio trading a basket of 4 stocks. I was wondering if
>   anyone
>   >   >  
would care to share any ideas on how you use the PositionScore
>   >   >  
function to rank your candidate list (using regular mode, not
>   >   >  
rotational mode). I've tried combinations of turnover and
>   volatility,
>   >   >  
but I'd like to try other ideas. I'm not asking anyone to give
>   away
>   >   >  
any secrets, and, yes, I am aware of TJ's example in the
help file
>   >   >  
(PositionScore = 100 -RSI());), but I was just looking for
>   more ideas.
>   >   >  
I'm not even sure if this question is too vague or not. If it
>   is, I'm
>   >   >  
sure you'll tell me. TIA.
>   >   >  
>
>   >   >  
> Al Venosa
>   >   >  
> advenosa@xxxx
>   >   >  
>
>   >   >  
>
>   >   >  
> ---
>   >   >  
> Outgoing mail is certified Virus Free.
>   >   >  
> Checked by AVG anti-virus system (http://www.grisoft.com).
>   >   >  
> Version: 6.0.543 / Virus Database: 337 - Release Date:
>   11/21/2003
>   >   >
>   >   >
>   >  
>         Yahoo! Groups Sponsor
>   >   >
>   >   >
>   >   >
>   >   >  
Send BUG REPORTS to bugs@xxxx
>   >   >  
Send SUGGESTIONS to suggest@xxxx
>   >   >  
-----------------------------------------
>   >   >  
Post AmiQuote-related messages ONLY to:
amiquote@xxxxxxxxxxxxxxx
>   >   >  
(Web page: http://groups.yahoo.com/group/amiquote/messages/)
>   >   >  
--------------------------------------------
>   >   >  
Check group FAQ at:
>   >   <a
href="">http://groups.yahoo.com/group/amibroker/files/groupfaq.html
>   >   >
>   >   >  
Your use of Yahoo! Groups is subject to the Yahoo! Terms of
>   Service.
>   >
>   >
>  
>         Yahoo! Groups Sponsor
>  
>              
ADVERTISEMENT
>   >
>   >
>   >
>   >
>   >   Send BUG REPORTS
to bugs@xxxx
>   >   Send SUGGESTIONS
to suggest@xxxx
>   >  
-----------------------------------------
>   >   Post
AmiQuote-related messages ONLY to: amiquote@xxxxxxxxxxxxxxx
>   >   (Web page: <a
href="">http://groups.yahoo.com/group/amiquote/messages/)
>   >  
--------------------------------------------
>   >   Check group FAQ
at:
>   <a
href="">http://groups.yahoo.com/group/amibroker/files/groupfaq.html
>   >
>   >   Your use of
Yahoo! Groups is subject to the Yahoo! Terms of
Service.
> 
> 
>        
Yahoo! Groups Sponsor
>              
ADVERTISEMENT
> 
> 
> 
> 
>   Send BUG REPORTS to bugs@xxxx
>   Send SUGGESTIONS to suggest@xxxx
>  
-----------------------------------------
>   Post AmiQuote-related messages
ONLY to: amiquote@xxxxxxxxxxxxxxx
>   (Web page: <a
href="">http://groups.yahoo.com/group/amiquote/messages/)
>  
--------------------------------------------
>   Check group FAQ at:
> <a
href="">http://groups.yahoo.com/group/amibroker/files/groupfaq.html
> 
>   Your use of Yahoo! Groups is
subject to the Yahoo! Terms of Service.



Send BUG
REPORTS to bugs@xxxxxxxxxxxxx<span
>
Send SUGGESTIONS to suggest@xxxxxxxxxxxxx
-----------------------------------------
Post AmiQuote-related messages ONLY to:
amiquote@xxxxxxxxxxxxxxx 
(Web page: <a
href="">http://groups.yahoo.com/group/amiquote/messages/)
--------------------------------------------
Check group FAQ at: <a
href="">http://groups.yahoo.com/group/amibroker/files/groupfaq.html


Your use of
Yahoo! Groups is subject to the Yahoo!
Terms of Service. 



<font size=3
face="Times New Roman">





Do you Yahoo!?
<a
href="">New
Yahoo! Photos - easier uploading and sharing 



<font size=2
face="Courier New">Send BUG REPORTS to
bugs@xxxxxxxxxxxxx<span
>
Send SUGGESTIONS to suggest@xxxxxxxxxxxxx
-----------------------------------------
Post AmiQuote-related messages ONLY to:
amiquote@xxxxxxxxxxxxxxx 
(Web page: <a
href="">http://groups.yahoo.com/group/amiquote/messages/)
--------------------------------------------
Check group FAQ at: <a
href="">http://groups.yahoo.com/group/amibroker/files/groupfaq.html


Your use of
Yahoo! Groups is subject to the Yahoo!
Terms of Service. 








Send BUG REPORTS to bugs@xxxxxxxxxxxxx
Send SUGGESTIONS to suggest@xxxxxxxxxxxxx
-----------------------------------------
Post AmiQuote-related messages ONLY to: amiquote@xxxxxxxxxxxxxxx 
(Web page: http://groups.yahoo.com/group/amiquote/messages/)
--------------------------------------------
Check group FAQ at: http://groups.yahoo.com/group/amibroker/files/groupfaq.html








Yahoo! Groups Sponsor


  ADVERTISEMENT 









Yahoo! Groups Links
To visit your group on the web, go to:http://groups.yahoo.com/group/amibroker/ 
To unsubscribe from this group, send an email to:amibroker-unsubscribe@xxxxxxxxxxxxxxx 
Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.