|
PureBytes Links
Trading Reference Links
|
Gaius Marius <magnus@xxxxxxxxxxx> wrote:
> Anyone care to discuss Benoit Mandelbrot's article in Scientific
American,
> "A Multifractal Walk down Wall St." ? Anyone read it? If you did, have
you
> found anything of value you'd care to discuss or disclose? ;-)
>
Given the target audience of the article, I think BM did a nice job in
explaining how fractals can be used to demonstrate and model the vagaries
of the stock market. As a trader with a scientific bent, however, I must
admit that I found many of the other articles in the magazine more
interesting!
But, from a trading standpoint, I think the following points are relevant.
1. BM concludes that fractal modelling techniques do not enable you to
forecast prices. I agree, but perhaps Bill Williams wouldn't.
2. His techniques demonstrate what any long-in-the-tooth trader will
probably have discovered: that markets can exhibit any type of behaviour,
and that such behaviour can last longer than might reasonably be expected,
and can change at the drop of a hat. This is why back-testing over a long
time relative to your trading timescale is vital.
3. Whatever has happened in the past will be exceeded in the future. So
your maximum drawdown found by back-testing will *always* be exceeded one
day - but you've no idea when. This was borne out for me last month, when
my previous record best and worst trading days were both exceeded in the
same week, and the previous records had stood for over 5 years! (Luckily,
the best came first, and more than paid for the worst.)
4. If you remove the labels from the axes of a chart, it is not possible to
tell the timescale of the chart. Therefore, claims by systems vendors that
their system will work on all time scales are probably correct, with the
possible exception of very short timescales where transaction costs are too
high a percentage of the gross return.
For me, a very interesting thing about the article is that it is featured
on the cover of Scientific American. Some of you may remember that Time and
?Newsweek have successfully pinpointed major turning points when the
markets made their front covers. Has the mantle passed to SA?!
Hugh.
|