|
PureBytes Links
Trading Reference Links
|
Hi Pal –
I agree with Katz and McCormick that the
likelihood of a system being profitable is inversely proportional to the number
of parameters.
But I don’t understand how the system you
describe in your first paragraph could have only one parameter. Do you
mean one variable that you change, but lots of others that have been determined
some time in the past and do not change? If so, then they all
count. So do the ones that were tried and discarded.
Howard
-----Original Message-----
From: palsanand
[mailto:palsanand@xxxxxxxxx]
Sent: Sunday,
November 16, 2003<span
> <font
size=2 face=Tahoma>10:56 AM<font
size=2 face=Tahoma>
To: amibroker@xxxxxxxxxxxxxxx
Subject: [amibroker] Re: Backtest
using equity curve
<font size=2
face="Courier New">My primary trading system is
very simple in the sense that it has <font size=2
face="Courier New">
only
one parameter (the lookback MA period), and it generally leads <font
size=2 face="Courier New">
to
a robust system. It is objective (non-optimized and parameters <font
size=2 face="Courier New">
are
never subject to change) and unique in the sense it is both trend-<font
size=2 face="Courier New">
following
(continuation of a previous trend or breakout) and counter-<font
size=2 face="Courier New">
trend
following (start of a new trend) at the same-time. The trend <font
size=2 face="Courier New">
and
counter-trend following features of the MA based systems are <font
size=2 face="Courier New">
highly
desirable because it resists becoming outdated as markets <font
size=2 face="Courier New">
change
character (personality). Independent of the fundamentals <font
size=2 face="Courier New">
driving
the market, these features are designed to capture extended <font
size=2 face="Courier New">
runs
in both bullish and bearish directions. The Verification and <font
size=2 face="Courier New">
Interpretation
of the signals Detected by this system was a great <font
size=2 face="Courier New">
challenge,
but I was able to use good filters (OB/OS) and use <font
size=2 face="Courier New">
Volatility
(non-trend component of a signal) to optimize my entry <font
size=2 face="Courier New">
points.
A robust system can be categorized as one that stands a good <font
size=2 face="Courier New">
chance
(probability) of working in the future as it has worked in the <font
size=2 face="Courier New">
past,
i.e, it is tough (able to handle all markets and conditions <font
size=2 face="Courier New">
regardless
of size and nature) and long-lasting (durable).<font size=2
face="Courier New">
As
discussed in a recent STOCKS & COMMODITIES article by Jeffrey Owen <font
size=2 face="Courier New">
Katz
and Donna McCormick, a rule of thumb in evaluating trading <font
size=2 face="Courier New">
systems
is that the more parameters a system has, the less robust the <font
size=2 face="Courier New">
system
is. Taken to the extreme, many fitting parameters can be used <font
size=2 face="Courier New">
to
curve-fit past data to eliminate all whipsaws while maintaining <font
size=2 face="Courier New">
good
performance. The potential of such a system working in the real <font
size=2 face="Courier New">
world
is nil...<span
>
rgds,
Pal
---
In amibroker@xxxxxxxxxxxxxxx, "Dave Merrill" <dmerrill@xxxx> <font
size=2 face="Courier New">
wrote:<font
size=2 face="Courier New">
>
agreed. if the fact that a trading system did well in the past has <font
size=2 face="Courier New">
no<font
size=2 face="Courier New">
>
bearing whatsoever on whether it does well in the future, how can <font
size=2 face="Courier New">
we
know
>
anything at all about the future performance of a proposed trading <font
size=2 face="Courier New">
system?<font
size=2 face="Courier New">
>
>
dave
>
>
The gambler¡Çs fallacy is a fallacy because the gambler ignores <font
size=2 face="Courier New">
the<font
size=2 face="Courier New">
>
independence of the outcomes and looks for patterns that do not <font
size=2 face="Courier New">
exist.
If
>
we have designed trading systems based on recognition of patterns <font
size=2 face="Courier New">
that<font
size=2 face="Courier New">
>
precede profitable trading opportunities, and if those patterns are<font
size=2 face="Courier New">
>
persistent, then we no longer have random, independent outcomes. <font
size=2 face="Courier New">
Our<font
size=2 face="Courier New">
>
trading systems do have serial dependencies and upward sloping <font
size=2 face="Courier New">
equity<font
size=2 face="Courier New">
>
curves. So analysis of the equity curve provides an indication of <font
size=2 face="Courier New">
the<font
size=2 face="Courier New">
>
health of the trading system.<span
>
>
>
>
>
Howard<span
>
<font size=2
color="#003399" face="Times New Roman">Send
BUG REPORTS to <span
>bugs@xxxxxxxxxxxxx<font size=2
face="Courier New">
Send
SUGGESTIONS to suggest@xxxxxxxxxxxxx<font size=2
face="Courier New">
-----------------------------------------<font
size=2 face="Courier New">
Post
AmiQuote-related messages ONLY to: <font size=2
face="Courier New">amiquote@xxxxxxxxxxxxxxx<font
size=2 face="Courier New"> <font
size=2 face="Courier New">
(Web
page: http://groups.yahoo.com/group/amiquote/messages/)<font
size=2 face="Courier New">
--------------------------------------------<font
size=2 face="Courier New">
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@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
Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.
|