!! : )) )
>
> Cheers,
> Mich
>
>
>
> - Original Message -
> From: Paul Ho
> To: amibroker@yahoogroups.com
> Sent: Friday, November 17, 2006 3:26 PM
> Subject: RE: [amibroker] Re: Polynomial Trendlines
>
>
> Thank mich for the info
> So we hav
riday, November 17, 2006 3:26 PM
Subject: RE: [amibroker] Re: Polynomial Trendlines
Thank mich for the info
So we have a mechanism to optimize the order of the AR estimator. There
remains a couple of interesting
areas that would affect the performance of this linear predictor
1. The No of Sample
measure to minimise?
Any thoughts?
Paul.
_
From: amibroker@yahoogroups.com [mailto:[EMAIL PROTECTED] On Behalf
Of Tom Tom
Sent: Thursday, 16 November 2006 12:28 PM
To: amibroker@yahoogroups.com
Subject: Re: [amibroker] Re: Polynomial Trendlines
rmserror is the white (theoricaly if AR fitting
ker@yahoogroups.com
Sent: Wednesday, November 15, 2006 11:55 PM
Subject: RE: [amibroker] Re: Polynomial Trendlines
Yes Mich, I noticed that as well, In addition,
Currently, memcof seems to calculate the rmserror as sum(data^2) - sum(1 -
reflection Coeff^2).
Is this valid? if not what do you use to calcul
Behalf
Of Tom Tom
Sent: Thursday, 16 November 2006 7:56 AM
To: amibroker@yahoogroups.com
Subject: Re: [amibroker] Re: Polynomial Trendlines
Hi !
Thanks Paul !
It is around the same for MEM yes. I find a way to compute it during the
recursive process (as you tell it).
I have made comparaison
n time is a little
> longer ...
>
> --- In [EMAIL PROTECTED] <mailto:amibroker%40yahoogroups.com>
ps.com,
> "Tomasz Janeczko"
> wrote:
> >
> > For that you need Fourier transform and FFT is coming as a built
> in function in 4.86
> >
> > Be
ke that of
Warren in his MEM article.
Cheers
Paul.
From: amibroker@yahoogroups.com
[mailto:[EMAIL PROTECTED] On Behalf Of FredSent:
Saturday, 7 October 2006 12:48 AMTo:
amibroker@yahoogroups.comSubject: [amibroker] Re: Polynomial
Trendlines
TJ,I have long since had FFT capability in
;
> _
>
> From: amibroker@yahoogroups.com [mailto:[EMAIL PROTECTED]
On Behalf
> Of Fred
> Sent: Wednesday, 25 October 2006 10:59 PM
> To: amibroker@yahoogroups.com
> Subject: [amibroker] Re: Polynomial Trendlines
>
>
>
> Yes ... I have had it running in AF
PMTo:
amibroker@yahoogroups.comSubject: [amibroker] Re: Polynomial
Trendlines
Yes ... I have had it running in AFL / VBS for quite awhile ... If
you look at old ( 83 - 84 ) issues of TASC you'll note that there were
others using maximum entropy years before Ehler's first mentioning it in
ll.edu/nr/bookcpdf/c13-7.pdf
>
>
>
> Have you had a look?
>
>
>
> Paul.
>
> _
>
> From: amibroker@yahoogroups.com [mailto:[EMAIL PROTECTED]
On Behalf
> Of Fred
> Sent: Wednesday, 4 October 2006 9:27 PM
> To: amibroker@yahoogroups.co
?
Paul.
From:
amibroker@yahoogroups.com [mailto:amibroker@yahoogroups.com] On Behalf Of Fred
Sent: Wednesday, 4 October 2006
9:27 PM
To: amibroker@yahoogroups.com
Subject: [amibroker] Re:
Polynomial Trendlines
Ohhh ... I thought you meant MESA i.e. Maximum Entropy Spectral
quot;)
Best regards,
Tomasz Janeczko
amibroker.com
- Original Message -
From: "vlanschot" <[EMAIL PROTECTED]>
To:
Sent: Sunday, October 08, 2006 1:04 PM
Subject: [amibroker] Re: Polynomial Trendlines
> Look forward to it TJ. Just wondered whether you've considered
&g
is coming as a built
in function in 4.86
>
> Best regards,
> Tomasz Janeczko
> amibroker.com
> - Original Message -
> From: "Fred" <[EMAIL PROTECTED]>
> To:
> Sent: Friday, October 06, 2006 3:48 AM
> Subject: [amibroker] Re: Polynomial Trendlines
Note that the bottom of the code says ...
// *
// *
// * Demo AFL to use PolyFit
// *
// *
Feel free to change whatever you want there to accomplish your
goal ... I would think of the
Title: Polynomial Trendlines
Hi
Fred,
I
would like to change your PolyFit function that I could write a system around
using it. Something like buy/sell when the slope of the line changes or
the slope changes a certain percentange of the latest high/low of the
line. The way you have t
> - Original Message -
> From: "Fred" <[EMAIL PROTECTED]>
> To:
> Sent: Friday, October 06, 2006 6:41 PM
> Subject: [amibroker] Re: Polynomial Trendlines
>
>
> > Excellent ... One more question if I may ... You aren't using an
> >
17, p.
93, June 1969
Best regards,
Tomasz Janeczko
amibroker.com
- Original Message -
From: "Fred" <[EMAIL PROTECTED]>
To:
Sent: Friday, October 06, 2006 6:41 PM
Subject: [amibroker] Re: Polynomial Trendlines
> Excellent ... One more question if I may ... You aren
ut array for FFT must NOT contain any Null
values. Use Nz() function to convert Nulls to zeros
>
> if you are not sure that input array is free from nulls.
>
>
> Best regards,
> Tomasz Janeczko
> amibroker.com
> - Original Message -
> From: "Fred"
ion to convert Nulls to zeros
if you are not sure that input array is free from nulls.
Best regards,
Tomasz Janeczko
amibroker.com
- Original Message -
From: "Fred" <[EMAIL PROTECTED]>
To:
Sent: Friday, October 06, 2006 4:47 PM
Subject: [amibroker] Re: Polynomial Trendl
From:
Rakesh
Sahgal
To: amibroker@yahoogroups.com
Sent: Friday, October 06, 2006 12:54
PM
Subject: Re: [amibroker] Re: Polynomial
Trendlines
That is very welcome news indeed. As per your planned release
schedule when do you think you will be releasing 4.86?Rakesh
On 10
AIL PROTECTED]> > wrote:>>>> For
that you need Fourier transform and FFT is coming as a built > in
function in 4.86>> >> Best regards,>> Tomasz
Janeczko>> amibroker.com>> - Original Message -
>> From: "Fred" <[EMAIL PROTE
-
> From: "Fred" <[EMAIL PROTECTED]>
> To:
> Sent: Friday, October 06, 2006 3:48 AM
> Subject: [amibroker] Re: Polynomial Trendlines
>
>
> > Now if someone can take this method and/or AFL or at least
provide a
> > how to that takes us into Trigomet
Great and thanks Tomasz that will help me a lot
...
Ton Sieverding.
- Original Message -
From:
Tomasz
Janeczko
To: amibroker@yahoogroups.com
Sent: Friday, October 06, 2006 9:52
AM
Subject: Re: [amibroker] Re: Polynomial
Trendlines
For that you
Tomasz Janeczkoamibroker.com- Original Message -From: "Fred" <
[EMAIL PROTECTED]>To: <amibroker@yahoogroups.com>Sent: Friday, October 06, 2006 3:48 AMSubject: [amibroker] Re: Polynomial Trendlines
> Now if someone can take this method and/or AFL or at least provide a> how
For that you need Fourier transform and FFT is coming as a built in function in
4.86
Best regards,
Tomasz Janeczko
amibroker.com
- Original Message -
From: "Fred" <[EMAIL PROTECTED]>
To:
Sent: Friday, October 06, 2006 3:48 AM
Subject: [amibroker] Re: Polynomial Trend
t; > Polynomial TrendlinesFred,
> > > >
> > > > There have been a lot of posting on this subject. Your one
> > image
> > > however is a very powerful message of its potential.
> > > >
> > > > Now I have to go back and
nd
> a
> > good reference to study.
> > >
> > > Anyone using it succesfully now?
> > >
> > > Ara
> > > - Original Message -
&g
of posting on this subject. Your one
> image
> > however is a very powerful message of its potential.
> > >
> > > Now I have to go back and review all the post ... hoping to find
> a
> > good reference to study.
> > >
> > > Anyone using it succesf
back and review all the post ... hoping to find
a
> good reference to study.
> >
> > Anyone using it succesfully now?
> >
> > Ara
> > ----- Original Message -----
> > From: Fred Tonetti
> > To: amibroker@yahoogroups.com
> > Sent: Tuesday, October 03, 200
t;
>
> _
>
> From: amibroker@yahoogroups.com [mailto:[EMAIL PROTECTED]
On Behalf
> Of Fred
> Sent: Thursday, 28 September 2006 11:36 AM
> To: amibroker@yahoogroups.com
> Subject: [amibroker] Re: Polynomial Trendlines
>
>
>
> I know his Hilbert is th
@yahoogroups.com
Sent: Wednesday, October 04, 2006 7:04
AM
Subject: Re: [amibroker] RE: Polynomial
Trendlines
Hi
Fred.I applied your formula but not works. Theis message
appeared:Order Polynomial Fit.afl contains an invalid path.What
can I do?Thanks
-
Original
ubject: [amibroker] RE: Polynomial Trendlines
Oops …
Meant to include this visual …
Green is calculated … White is
extrapolated …
I am using the free version of SPAMfighter for private users.It has removed 8588 spam emails to date.Paying users do no
>
> From: [EMAIL PROTECTED]ps.com
[mailto:[EMAIL PROTECTED]ps.com]
On Behalf
> Of Fred
> Sent: Wednesday, 27 September 2006 10:50 PM
> To: [EMAIL PROTECTED]ps.com
> Subject: [amibroker] Re: Polynomial Trendlines
>
>
>
> AFL is capable of almost all the same things
tti
> To: amibroker@yahoogroups.com
> Sent: Tuesday, October 03, 2006 3:32 PM
> Subject: [amibroker] RE: Polynomial Trendlines
>
>
> Oops .
>
>
>
> Mea
- Original Message -
From:
Fred
Tonetti
To: amibroker@yahoogroups.com
Sent: Tuesday, October 03, 2006 3:32
PM
Subject: [amibroker] RE: Polynomial
Trendlines
Oops
Meant to include this
visual
Green is calculated
White is
The PolyFit & GaussianElimination Functions use only the data you
pass it ...
The Demo Main AFL was set up to use Beg & End Range markers but you
can easily change those to whatever you like.
The extrapolations are only calculated once the fit as of some bar
has been done. If you click CHECK
Title: Polynomial Trendlines
Oops …
Meant to include this visual …
Green is calculated … White is
extrapolated …
I am using the free version of SPAMfighter for private users.It has removed 8588 spam emails to date.Paying users do not have this message in their emails.Try
; From: amibroker@yahoogroups.com [mailto:[EMAIL PROTECTED]
On Behalf
> Of Fred
> Sent: Wednesday, 27 September 2006 10:50 PM
> To: amibroker@yahoogroups.com
> Subject: [amibroker] Re: Polynomial Trendlines
>
>
>
> AFL is capable of almost all the same things that Fortran is and
27, 2006 5:50 AM
> To: amibroker@yahoogroups.com
> Subject: [amibroker] Re: Polynomial Trendlines
>
>
> AFL is capable of almost all the same things that Fortran is and
if
> one is capable of constructing a For loop then it is not difficult
(
> REALLY ) to go to Numeric Recipes an
s.com
Subject: [amibroker] Re: Polynomial Trendlines
AFL is capable of almost all the same things that Fortran is and if
one is capable of constructing a For loop then it is not difficult (
REALLY ) to go to Numeric Recipes and get their Fortran 77 code that
reads almost like AFL and with some s
…. And some of them already exist as
dll published in the dll user group, e.g. MESA
From:
amibroker@yahoogroups.com [mailto:[EMAIL PROTECTED] On Behalf Of Fred
Sent: Wednesday, 27 September 2006
10:50 PM
To: amibroker@yahoogroups.com
Subject: [amibroker] Re:
Polynomial
AFL is capable of almost all the same things that Fortran is and if
one is capable of constructing a For loop then it is not difficult (
REALLY ) to go to Numeric Recipes and get their Fortran 77 code that
reads almost like AFL and with some slight modifications will fill
the bill for
Cubic S
Will do! Thanks, Ed.
Dan
--- In amibroker@yahoogroups.com, "Ed Hoopes" <[EMAIL PROTECTED]>
wrote:
>
> Dan,
>
> Try a weighted average of 2 LinearRegression's like:
>
> Composite = 2*LR(10) + 1*LR(20) / 3
>
> Put in lengths&weights appropriate for your time frame.
Backtesting
> this wil
Hello Steve
How do you use LSMA in your trading?
Regards
Wes
--- In amibroker@yahoogroups.com, "scourt2000" <[EMAIL PROTECTED]> wrote:
>
>
> A least squares moving average has served me well. I consistently
> make money with it on the ER2.
>
> Steve
>
Please note that this group is for
Dan,
Try a weighted average of 2 LinearRegression's like:
Composite = 2*LR(10) + 1*LR(20) / 3
Put in lengths&weights appropriate for your time frame. Backtesting
this will of course drive you crazy ! :)
Ed
--- In amibroker@yahoogroups.com, "d_hanegan" <[EMAIL PROTECTED]> wrote:
>
> Thanks
I also use the least squares fit to a straight line to daytrade YM,
ER2. It works just fine. (even though I have higher order fits
available to me.)
ReefBreak
--- In amibroker@yahoogroups.com, "scourt2000" <[EMAIL PROTECTED]> wrote:
>
>
> A least squares moving average has served me well. I con
Thanks, Steve. I will check it out.
Dan
--- In amibroker@yahoogroups.com, "scourt2000" <[EMAIL PROTECTED]> wrote:
>
>
> A least squares moving average has served me well. I consistently
> make money with it on the ER2.
>
> Steve
>
Please note that this group is for discussion between
Thanks, Ed. I was hoping to find something that was not quite as
jumpy as a linear regression line. I had typed Closing prices into
Excel and charted Poly Lines and it looks like it has SOME promise.
I also checked out the threads on Sigma Bands and they too SEEM to
have some viability. I a
A least squares moving average has served me well. I consistently
make money with it on the ER2.
Steve
Please note that this group is for discussion between users only.
To get support from AmiBroker please send an e-mail directly to
SUPPORT {at} amibroker.com
For other support mater
I have experimented with a cubic fit. By the time you allow 2
inflection points, the line is so flexible that it looks almost
identical to a moving average. My testing shows that MA's are better.
ReefBreak
--- In amibroker@yahoogroups.com, "John Tierney" <[EMAIL PROTECTED]> wrote:
>
> I have a
I have written a least squares fit to a quadratic equation. It was
quite difficult due to the computation of the coefficient of the x^2
term. The problem is that AB uses single precision math, and the
computation would 'blow up' every so often because the coeff of x^2 is
the difference between tw
51 matches
Mail list logo