|
PureBytes Links
Trading Reference Links
|
I have a copy in my office. If you are going to be in the Wall Street area
call me (212 897 8125). I don't own the study so I cannot redistribute it
electronically. The study was given at a conference hosted by the
CBOE/CBOT/CME .. the CBOE point person is Matt Moran. You might want to e
mail him and see what can be made available.
-----Original Message-----
From: Jeff Haferman [mailto:jeff_haferman@xxxxxxxxx]
Sent: Sunday, February 03, 2002 2:06 PM
To: realtraders@xxxxxxxxxxxxxxx
Subject: Re: [RT] VIX and VXN from their father
Well Alex,
I would like to see Whaley's study if it is available in
print or electronic form anywhere.
A very interesting methodology for examining the predictability
of the markets is given in Ch. 13 of Edgar Peters' "Chaos and
Order in the Capital Markets"... it gets pretty mathematically
involved, dealing with embedding dimensions and correlation
integrals and Lyapunov exponents and such, but I can summarize
that Peters found an "embedding dimension" of about 3 for the
S&P 500, and he recommended - for stability - an embedding
dimension of 4.
What this means is, there is a function of 4 independent variables which
can be used to forecast the SPX. However, it doesn't say
what the function is (it could be chaotic and highly non-linear),
nor what the 4 variables are.
Brock, Hsieh, and Lebaron (Nonlinear Dynamic, Chaos, and
Instability) cite several studies that show embedding dimensions
of between 6 and 7 for various markets... however, they use
daily data, whereas Peters uses monthly data... Peters explains
that the monthly data contains less noise and therefore is
a better predictor.
Anyway, it's all very interesting stuff. I certainly think
Ron could certainly be using VIX and VXN to get "approximate"
ranges.
Jeff
Ronald McEwan wrote:
>----__JNP_000_61e9.2c0a.0952
>Content-Type: text/plain; charset=US-ASCII
>Content-Transfer-Encoding: 7bit
>
>This is very interesting. I have been using the VIX ( and the VXN ) as
>inputs to a Montecarlo Simulation model I develeoped to predict the
>approximate price ranges for the Oex and Ndx. I never realized that this
>could not be done ?
>
>Ron McEwan
>
>On Sat, 2 Feb 2002 19:13:31 -0500 "Jacobson, Alex"
><AJacobson@xxxxxxxxxxxxxx> writes:
>> I was at the annual CBOE/CBOT/CME Risk Management Conference this
>> week. On
>> Friday Bob Whaley of Fuqua .. the fellow who created VIX and VXN for
>> the
>> CBOE did a piece analyzing volatility indexes. He, in effect, did
>> an
>> analysis of the predictive value of market vol. indexes as
>> predictive tools
>> ... both short term and long term. I'll simplify his conclusions.
>> It
>> doesn't work as forward price indicator. I don't know if the CBOE
>> will or
>> won't post his study on their Website. The CBOE never proposed the
>> index as
>> a predictive tool of direction ... it was offered as a gauge of
>> subsequent
>> market return volatility.
>>
>> One really interesting analysis he did was on the spread of VXN over
>> VIX as
>> measure of concern over tech.
>>
>> Alex Jacobson
>> Vice President
>> Business Development
>> International Securities Exchange
>> (212)897 8125
>> (877)720 9918(SKYPAGE)
>> ajacobson@xxxxxxxxxxxxxx
>>
>>
To unsubscribe from this group, send an email to:
realtraders-unsubscribe@xxxxxxxxxxxxxxx
Your use of Yahoo! Groups is subject to http://docs.yahoo.com/info/terms/
------------------------ Yahoo! Groups Sponsor ---------------------~-->
Access Your PC from Anywhere
It's Easy. It's Fast. - Free Download
http://us.click.yahoo.com/2njxPB/zakDAA/cosFAA/zMEolB/TM
---------------------------------------------------------------------~->
To unsubscribe from this group, send an email to:
realtraders-unsubscribe@xxxxxxxxxxxxxxx
Your use of Yahoo! Groups is subject to http://docs.yahoo.com/info/terms/
|