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

RE: [EquisMetaStock Group] Re: Is a Monte Carlo simulation useless ?



PureBytes Links

Trading Reference Links

I use Monte Carlo for back-testing stock portfolios.  If I have a system
that generates between 0 and 10 trades a day (EOD) and have a holding period
of 5 to 10 days, the its likely I can't take all the trades unless my bet
size is very small. If I want to test the portfolio through time, I need a
mechanism to select trades at random from the qualifying trades according to
my trade sizing rules. Using Monte Carlo I can do this, and then run the
same thing another 1000 times to get a statistically meaningful idea of what
might have happened in real life. Then I can run it again with different
money management rules and see what the impact is. 

I use TradeSim for this, but maybe there are other Monte Carlo simulators
out there that can do something similar. Anyway, for portfolio analysis the
method is indispensable IMHO.

Andrew

-----Original Message-----
From: equismetastock@xxxxxxxxxxxxxxx [mailto:equismetastock@xxxxxxxxxxxxxxx]
On Behalf Of jawjahtek
Sent: Tuesday, May 10, 2005 8:56 PM
To: equismetastock@xxxxxxxxxxxxxxx
Subject: [EquisMetaStock Group] Re: Is a Monte Carlo simulation useless ?


Hello Marco,

I would not call Monte Carlo simulation useless, but I do not have the 
high expectations that I had when I first learned about it. My data 
provider (CSI) has a Monte Carlo simulator in the software. After using 
it, I had the following thoughts:
1. It did give me a good idea of the probability of ruin as well as 
other statistics for the system trades that I input. The simulation 
told me what would happen if the set of trades was done with more than 
a thousand different sequences.
2. Unfortunately, time is a linear phenomena (i.e., a series of events 
only happens once as time moves on). I will never know (until I trade a 
given system in real time) if my series of trades will be near the mean 
of the Monte Carlo simulation or an outlier (billionaire or bust). Certainly
Decision Analysis using Monte Carlo simulation is a well 
established methodology in the business world. But trading is like 
life, you only it once.

Bottom line for me: another holy grail hope sent to the trash heap; but 
not wasted effort.


Ross


--- In equismetastock@xxxxxxxxxxxxxxx, Khamsina11 <Khamsina11@xxxx> 
wrote:
> 
> Hi,
> 
> I would like to know what are the advantages/drawbacks of the Monte
> Carlo simulation for a trading system.
> 
> Thanks in advance for help,
> 
> Regards,
> 
> Marco





 
Yahoo! Groups Links



 






------------------------ Yahoo! Groups Sponsor --------------------~--> 
In low income neighborhoods, 84% do not own computers.
At Network for Good, help bridge the Digital Divide!
http://us.click.yahoo.com/EpW3eD/3MnJAA/cosFAA/BefplB/TM
--------------------------------------------------------------------~-> 

 
Yahoo! Groups Links

<*> To visit your group on the web, go to:
    http://groups.yahoo.com/group/equismetastock/

<*> To unsubscribe from this group, send an email to:
    equismetastock-unsubscribe@xxxxxxxxxxxxxxx

<*> Your use of Yahoo! Groups is subject to:
    http://docs.yahoo.com/info/terms/