Welcome Guest, please sign in to participate in a discussion. Search | Active Topics |

Direction of the 'linear regression' line Rate this Topic:
Previous Topic · Next Topic Watch this topic · Print this topic ·
alfa75
Posted : Monday, December 28, 2009 1:38:10 PM
Registered User
Joined: 12/8/2007
Posts: 13
I want to include the drirection or slope of the 'linear regression' line into one of my scans. How can I do this?
Bruce_L
Posted : Monday, December 28, 2009 1:56:37 PM


Worden Trainer

Joined: 10/7/2004
Posts: 65,138
The formula for the Slope of a Linear Regression Line would depend on your specific settings. We should be able to help you create a formula if you provide your particular settings.

Using Linear Regression vs Classical Peaks/Valleys for Divergence Analysis

-Bruce
Personal Criteria Formulas
TC2000 Support Articles
alfa75
Posted : Monday, December 28, 2009 2:13:01 PM
Registered User
Joined: 12/8/2007
Posts: 13

I simply want to know if the 50 day Linear Regression line is trending up or down. Could be a grade/slope percentage (pos/neg)

Bruce_L
Posted : Monday, December 28, 2009 2:49:27 PM


Worden Trainer

Joined: 10/7/2004
Posts: 65,138
One way to write a formula for the Slope of a 50-Period Linear Regression would be:

(24.5 * C + 23.5 * C1 + 22.5 * C2 + 21.5 * C3 + 20.5 * C4 + 19.5 * C5 + 18.5 * C6 + 17.5 * C7 + 16.5 * C8 + 15.5 * C9 + 14.5 * C10 + 13.5 * C11 + 12.5 * C12 + 11.5 * C13 + 10.5 * C14 + 9.5 * C15 + 8.5 * C16 + 7.5 * C17 + 6.5 * C18 + 5.5 * C19 + 4.5 * C20 + 3.5 * C21 + 2.5 * C22 + 1.5 * C23 + .5 * C24 - .5 * C25 - 1.5 * C26 - 2.5 * C27 - 3.5 * C28 - 4.5 * C29 - 5.5 * C30 - 6.5 * C31 - 7.5 * C32 - 8.5 * C33 - 9.5 * C34 - 10.5 * C35 - 11.5 * C36 - 12.5 * C37 - 13.5 * C38 - 14.5 * C39 - 15.5 * C40 - 16.5 * C41 - 17.5 * C42 - 18.5 * C43 - 19.5 * C44 - 20.5 * C45 - 21.5 * C46 - 22.5 * C47 - 23.5 * C48 - 24.5 * C49) / 10412.5

You could return the sign of the Slope using (1 if positive and -1 if negative):

SGN(49 * (C - C49) + 47 * (C1 - C48) + 45 * (C2 - C47) + 43 * (C3 - C46) + 41 * (C4 - C45) + 39 * (C5 - C44) + 37 * (C6 - C43) + 35 * (C7 - C42) + 33 * (C8 - C41) + 31 * (C9 - C40) + 29 * (C10 - C39) + 27 * (C11 - C38) + 25 * (C12 - C37) + 23 * (C13 - C36) + 21 * (C14 - C35) + 19 * (C15 - C34) + 17 * (C16 - C33) + 15 * (C17 - C32) + 13 * (C18 - C31) + 11 * (C19 - C30) + 9 * (C20 - C29) + 7 * (C21 - C28) + 5 * (C22 - C27) + 3 * (C23 - C26) + C24 - C25)

So a formula that would return True when the 50-Period LR is positive would be:

49 * (C - C49) + 47 * (C1 - C48) + 45 * (C2 - C47) + 43 * (C3 - C46) + 41 * (C4 - C45) + 39 * (C5 - C44) + 37 * (C6 - C43) + 35 * (C7 - C42) + 33 * (C8 - C41) + 31 * (C9 - C40) + 29 * (C10 - C39) + 27 * (C11 - C38) + 25 * (C12 - C37) + 23 * (C13 - C36) + 21 * (C14 - C35) + 19 * (C15 - C34) + 17 * (C16 - C33) + 15 * (C17 - C32) + 13 * (C18 - C31) + 11 * (C19 - C30) + 9 * (C20 - C29) + 7 * (C21 - C28) + 5 * (C22 - C27) + 3 * (C23 - C26) + C24 - C25 > 0

And a formula that would return True when the 50-Period LR is negative would be:

49 * (C - C49) + 47 * (C1 - C48) + 45 * (C2 - C47) + 43 * (C3 - C46) + 41 * (C4 - C45) + 39 * (C5 - C44) + 37 * (C6 - C43) + 35 * (C7 - C42) + 33 * (C8 - C41) + 31 * (C9 - C40) + 29 * (C10 - C39) + 27 * (C11 - C38) + 25 * (C12 - C37) + 23 * (C13 - C36) + 21 * (C14 - C35) + 19 * (C15 - C34) + 17 * (C16 - C33) + 15 * (C17 - C32) + 13 * (C18 - C31) + 11 * (C19 - C30) + 9 * (C20 - C29) + 7 * (C21 - C28) + 5 * (C22 - C27) + 3 * (C23 - C26) + C24 - C25 < 0

-Bruce
Personal Criteria Formulas
TC2000 Support Articles
alfa75
Posted : Monday, December 28, 2009 3:13:48 PM
Registered User
Joined: 12/8/2007
Posts: 13
Who better than you?    .................."nobody!!!"  

Thanks!
Bruce_L
Posted : Monday, December 28, 2009 3:36:46 PM


Worden Trainer

Joined: 10/7/2004
Posts: 65,138
You're welcome.

-Bruce
Personal Criteria Formulas
TC2000 Support Articles
janmart
Posted : Saturday, January 9, 2010 9:02:37 PM
Registered User
Joined: 12/4/2004
Posts: 8

Just curious, why wouldn't you simply sort the Regression Line using VISUAL CHANGE?

Bruce_L
Posted : Monday, January 11, 2010 3:53:51 PM


Worden Trainer

Joined: 10/7/2004
Posts: 65,138
janmart,
The primary reason I use Personal Criteria Formulas versus Indicator Sorting is speed. It doesn't make a lot of difference on a small Watchlist, but on large Watchlists, Indicator Sorting can be quite slow. In addition, if I am using the same Sort on multiple Watchlists, I only need to calculate my PCFs once where if I'm using Indicator Sorting, it will need to recalculate every time I change Watchlists.

-Bruce
Personal Criteria Formulas
TC2000 Support Articles
Users browsing this topic
Guest-1

Forum Jump
You cannot post new topics in this forum.
You cannot reply to topics in this forum.
You cannot delete your posts in this forum.
You cannot edit your posts in this forum.
You cannot create polls in this forum.
You cannot vote in polls in this forum.