The "exact" Kurtosis (as you call
it), creates "windows" of spikes based on the look back periods. The
formula presented by me is a simpler version, which avoids those spikes in the
Kurtosis.
As you may be aware, Kurtosis
measures the "peak" of a distribution, using the mean and the standard
deviation. Again it depends on what method of mean you are taking from
the distribution. Whether you are taking the mean of a single day, the Moving
Average of the mean over a certain period, or the mathematical mean over a
certain period.
Its very subjective, and again user
specific. The kurtosis is supposed to give a bell curve, and
analysed.
This is my very humble submission,
of what little I know of kurtosis, and I admit I my be wrong.
Dusant
----- Original Message -----
Sent: Monday, March 07, 2005 11:44
AM
Subject: [EquisMetaStock Group] Re:
Skewness or biasedness and kurtosis..MG Ferreira and Dusant
I am not sure I understand you corretly, but there is a
standard formula for kurtosis, which is the 'exact' one I gave. The
'approx' is a lot easier to use in practise and can go back much
further (longer period). You can not implement the 'exact' in that
way in MS as far as I know, after about 20 periods you get some funny
error, so that is why there is an approx in the first place.
I
*think* dusant's formula measures the same thing, ie has the same idea in
it, but it is not the official kurtosis formula, if there is such as an
official formula.
Regards MG Ferreira TsaTsa EOD Programmer and
trading model builder http://tsatsaeod.ferra4models.com http://www.ferra4models.com
---
In equismetastock@xxxxxxxxxxxxxxx, "cardiop" <cardiop@xxxx>
wrote: > > MG Ferreira and Dusant... > >
Friends... > You presented two formulate for Kurtosis... formulate
Them > different and take the different graphs. What she would
be > formulates it exata? > Thank you >
Skill
Yahoo! Groups Sponsor |
ADVERTISEMENT
| |
|
Yahoo! Groups Links
Yahoo! India Matrimony: Find your life partner
online. |