Re: Re[3]: [RT] near a bottom

["Sergey" <tarassov@xxxxxxxxxx>]

I did a statistical research for zigzag trying to find statistically verified support/resistance levels.

 

Like finding statistically where should be the point C as the most probable support level. I do it as a distribution for the ratio between down and upward swings:

 

 

 

As an example, for Dow (data from 1885 till 2007, 5% zigzag used) the histogram for the ratio between down and upward swing looks like this:

 

 

 

The interesting thing is that there is some clustering in this distribution, i.e. we can specify some high probability zones for the support level.

 

More about it is here:

http://www.timingsolution.com/TS/Articles/waves_in_moon/waves_in_moon.htm

and here:

http://www.timingsolution.com/TS/Articles/tp_1/tp_1.htm

 

Best regards.

Sergey.

 

----- Original Message -----

From: Code 2

To: Clyde Lee

Sent: Tuesday, December 18, 2007 6:20 PM

Subject: Re[3]: [RT] near a bottom

My recollection is that Pearson's r assumes a normal distribution of
values. Remember that trends and price changes often do not behave in
accordance with a normal distribution -- just ask the Long-Term
Capital Management guys.

From: Clyde Lee <clydelee@xxxxxxxnet>
To: realtraders@yahoogroups.com
Date: Tuesday, December 18, 2007, 2:49:54 PM
Subject: [RT] near a bottom

I have been working on a strategy that uses the Pearson r Correlation
Coefficient as a means of estimating points of Change In Trend.

The attached picture is of 30 minute bars of ES.  You will notice that
in this scenario the CIT has been fairly well called.

That is said to note that the strategy called for the trend to turn
positive in the middle of the day -- so maybe near bottom ! ! !

Clyde

__._,_.___

Your email settings: Individual Email|Traditional
Change settings via the Web (Yahoo! ID required)
Change settings via email: Switch delivery to Daily Digest | Switch to Fully Featured
Visit Your Group | Yahoo! Groups Terms of Use | Unsubscribe

__,_._,___