|
PureBytes Links
Trading Reference Links
|
Maybe, just browse through the paper, and try to understand the
first numerical example. If you can follow that example, you can
use the Kalman filter in practise, as it shows how to apply the
formulas to something real and useful. I am sure it can be done
in MS. The most difficult part of the Kalman filter is to specify
the state-space representation of a system. Again, the example
gives one simple representation that is quite useful. I am sure
the Kalman filter can be coded in MS - you need variances and so on,
based on your state, so it must be easily possible. The first
step, however, is to specify your state. I had a mind, based on one
previous post, to write down code using the Kalman filter that just
forecasts if the market will go up or down tomorrow. The Kalman
is just a glorified, variable parameter exponential moving average,
to refer to some recent postings. Also, use all that code I gave
earlier on in this thread to do something similar to the Kalman.
Regards
MG Ferreira
TsaTsa EOD Programmer and trading model builder
http://www.ferra4models.com
http://fun.ferra4models.com
--- In equismetastock@xxxxxxxxxxxxxxx, khamsina11 <Khamsina11@xxxx> wrote:
>
> Hi MG,
>
> Thanks. Quite difficult to understand ( I am not very good at maths :-[
> ) but an interesting paper.
>
> It is a pity the Kalman filter can't be translated into MS language.
>
> Regards,
>
> Marco
>
>
>
> MG Ferreira a écrit :
>
> >Hi Marco,
> >
> >I finally found that article on an backup CD of yonder years,
> >luckily the CD still works! I've added a new page on our web site
> >where I make the Kalman stuff available. Go to
> >
> > http://www.ferra4models.com
> >
> >and select the 'Models' section. There is a subsection named
> >'Kalman filter' from which you can download the article.
> >
> >We also wrote quite a technical working paper on variable parameter
> >models (which uses Kalman filters extensively), but I could not find
> >an electronic copy on my PC. Must be on some CD somewhere.... It
> >was published in the SEE journal, but will also be presented in
> >Texas somewhere in June (I am co-author, and not really that much up
> >to date with these details....) I'll upload a copy of that to this
> >same page at some stage in the future - maybe.....
> >
> >Regards
> >MG Ferreira
> >TsaTsa EOD Programmer and trading model builder
> >http://www.ferra4models.com
> >http://fun.ferra4models.com
> >
> >
> >
> >
> >
> >--- In equismetastock@xxxxxxxxxxxxxxx, khamsina11 <Khamsina11@xxxx>
wrote:
> >
> >
> >>Hi MG,
> >>
> >>Thanks in advance ! :)
> >>
> >>Regards,
> >>
> >>Marco
> >>
> >>
> >>MG Ferreira a écrit :
> >>
> >>
> >>
> >>>Hi there,
> >>>
> >>>I am working on it - sort of. Years ago I wrote an introductory
> >>>article on the Kalman filter. It was never finished or published and
> >>>has a few known bugs in it, but was later on bought by a trader who
> >>>wanted to get to know the Kalman filter! I've upgraded computers so
> >>>many times since I fear the piece may be lost somewhere in digital
> >>>oblivion, but will upload it somewhere as soon as I find it. It
gives
> >>>a market oriented intro to the Kalman filter, all the formulas and a
> >>>few examples.
> >>>
> >>>Regards
> >>>MG Ferreira
> >>>TsaTsa EOD Programmer and trading model builder
> >>>http://www.ferra4models.com
> >>>http://fun.ferra4models.com
> >>>
> >>>
> >>>
> >>>--- In equismetastock@xxxxxxxxxxxxxxx, khamsina11 <Khamsina11@xxxx>
> >>>
> >>>
> >wrote:
> >
> >
> >>>
> >>>
> >>>
> >>>
> >>>>Hi MG,
> >>>>
> >>>>Might you post a MS code of the Kalman filter ?
> >>>>
> >>>>Regards,
> >>>>
> >>>>Marco
> >>>>
> >>>>
> >>>>
> >>>>MG Ferreira a écrit :
> >>>>
> >>>>
> >>>>
> >>>>
> >>>>
> >>>>>Just note! The stuff I gave is not the 'official' Kalman filter
> >>>>>and will probably be frowned upon by say a NASA engineer. But it
> >>>>>is something similar and we use such devices in our own work. We
> >>>>>sometimes also smooth the weights, so that one formula
> >>>>>
> >>>>> w1 = w1 + ...
> >>>>>
> >>>>>becomes
> >>>>>
> >>>>> w1 = 0.9 * w1 + 0.1 * ( w1 + ... )
> >>>>>
> >>>>>and we play around with the 0.9 amd 0.1 They should always sum to
> >>>>>1, and the higher the 0.9, the more smooth the weights will be.
This
> >>>>>is just an exponential moving average....
> >>>>>
> >>>>>For the rest, see below.
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>>I am interested on Kalman filter too, in term of training periods
> >>>>>>for the net, do you have any suggestion on how to determine the
> >>>>>>length of periods? If the period is too long, then could it be
> >>>>>>overtrained? If I can determine it, then the periods for
rescaling
> >>>>>>based on HHV(Abs(S),periods) could be found, will it be a good
> >>>>>>approach?
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>OK, we are not really training a net here, and even if we were, it
> >>>>>is arbitrary. Also see my comment on the next one. I suggest you
> >>>>>plot your indicator and visually inspect it. If it makes cycles,
> >>>>>see how long it takes to make one full cycle. Hopefully it is not
> >>>>>several years, but say 1 or 0.5 years. Then pick a period that
will
> >>>>>contain three of the previous cycles, say 3 or 1.5 years, and use
> >>>>>that. This is a long time, but we are only using it in the
> >>>>>
> >>>>>
> >rescaling,
> >
> >
> >>>>>so it should not be too much of a problem.
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>>I remember someone mentioned the ratio for period between training
> >>>>>>and out of sample should be following
> >>>>>>Training periods: 8
> >>>>>>Out of Sample periods: 1
> >>>>>>But he never mentioned about the rationale, and used it as a
rule of
> >>>>>>thumb, do you have any idea?
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>This is arbitrary. A real good, theoretical way to do this, is to
> >>>>>split the sample in ten periods. Then randomly choose 9, train it
> >>>>>on those 9, and test it on the rest. Now choose randomly a
different
> >>>>>9 sections, train and test on the remaining 1 and so on. It takes
> >>>>>forever to do something like this and we've used it only
rarely, but
> >>>>>it will make your Prof very happy! We more often use 20, 10 or
even
> >>>>>the last 5%, depending on the length of data. The more data we
have,
> >>>>>the more we can cut off to test on. But it is arbitrary. Again,
> >>>>>eyeball the data, and if it has a nice, complete cycle or two
in the
> >>>>>last say 10%, then you can use that to test and you will get a good
> >>>>>feel for how it will do in real life.
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>>According to your Message 16564, I have search for Woodes
Rogers on
> >>>>>>library and amazon, and found a book called "The speculative
> >>>>>>strategist", which did mention about Woodes Rogers' approach,
but it
> >>>>>>is too brief, does it the one you read?
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>That is the book!
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>>I think I need a few days to digest Kalman filter and to do some
> >>>>>>coding on it, and will reply to this topic soon under the same
> >>>>>>subject title
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>Again, those formulas may have bugs in them. So rather try to
graph
> >>>>>the ideas they embody and then you can use them as guides to
> >>>>>
> >>>>>
> >implement
> >
> >
> >>>>>your own. I look forward to hear from you!
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>>Thank you :>
> >>>>>>Eric
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>>
> >>>>>No problem!
> >>>>>
> >>>>>Regards
> >>>>>MG Ferreira
> >>>>>TsaTsa EOD Programmer and trading model builder
> >>>>>http://www.ferra4models.com
> >>>>>http://fun.ferra4models.com
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>Yahoo! Groups Links
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>>>
> >>>
> >>>
> >>>
> >>>
> >>>
> >>>Yahoo! Groups Links
> >>>
> >>>
> >>>
> >>>
> >>>
> >>>
> >>>
> >>>
> >>>
> >>>
> >>>
> >>>
> >
> >
> >
> >
> >
> >
> >
> >Yahoo! Groups Links
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
------------------------ Yahoo! Groups Sponsor --------------------~-->
In low income neighborhoods, 84% do not own computers.
At Network for Good, help bridge the Digital Divide!
http://us.click.yahoo.com/EpW3eD/3MnJAA/cosFAA/BefplB/TM
--------------------------------------------------------------------~->
Yahoo! Groups Links
<*> To visit your group on the web, go to:
http://groups.yahoo.com/group/equismetastock/
<*> To unsubscribe from this group, send an email to:
equismetastock-unsubscribe@xxxxxxxxxxxxxxx
<*> Your use of Yahoo! Groups is subject to:
http://docs.yahoo.com/info/terms/
|