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

Re: Optimal f and system optimization


  • To: metastock@xxxxxxxxxxxxx
  • Subject: Re: Optimal f and system optimization
  • From: rst@xxxxxxxxxxx (rudolf stricker)
  • Date: Sat, 14 Aug 1999 03:18:32 -0700
  • In-reply-to: <37919bc4.8775155@xxxxxxxxxxx>

PureBytes Links

Trading Reference Links


Sorry for the delay, I had to reconstruct a "frozen" hdisk. But now
all who inquired should have received the WEB article (pdf) and the
accompanying xls-file on the calculation of Weibull distributions from
discrete data in Excel.

But be warned: 
The article http://www.qualitydigest.com/jan99/html/body_weibull.html
does not deal with trading but with the reliability of jack-in-the-box
designs. So we have to adopt the given numerical recipes  to our need.
But because Weibull's distribution is heavily used to represent rare
events (eg in failure analysis in mechanical engineering) it can also
very nicely represent win and loss distributions in trading systems.

On Mon, 19 Jul 1999 10:39:17 -0700, Glen Wallace wrote:

>What distribution to use, is the $64,000 question.  Until that question is
>answered, we just have to limp along with the tools we have and a firm stop
>loss.

Imo, the Weibull distribution is a considerable contribution to answer
the above question. Especially the Weibull parameter beta (=
characteristic life = characteristic win or loss, when appropriately
applied to trading) provides a valid representation of the
"tail-iness" of win or loss distributions. Appropriately used in the
"goal function" for system optimization, it can help to optimize the
shape of e.g. loss distributions, which works hand in hand with the
"optimal f" optimization.

Have fun with Weibull's distribution.

mfg rudolf stricker
| Disclaimer: The views of this user are strictly his own.