[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [amibroker] Re: Monte Carlo analysis for trading systems



PureBytes Links

Trading Reference Links

Hi Brian --

You wrote:
"I am amazed at the low level of interest in the subject, by traders
in general, and also that 'we' haven't moved along very quickly,
since Pardo e.g. there's not a lot of quality books, on simulation
for trading, available."

I agree that there has been a relatively low level of interest.

I agree that when Bob Pardo's first book was published in 1992, it was the best available.  Since then there are several books that discuss trading systems development with varying degrees of understanding of the issues involved in modeling and simulation of financial trading systems.

As examples:

Perry Kaufman's "Trading Systems and Methods", 1992, followed by "New Trading Systems and Methods" in 2005.
Van Tharp's "Trade Your Way to Financial Freedom", 1998, and its Second Edition, 2007.

There is a fair amount of literature that discusses ARCH, GARCH, ARIMA, and related models.  But those are mathematically sophisticated, difficult to implement, and do not apply well to short term systems.

David Aronson's "Evidence-based Technical Analysis", 2007, is excellent and does recognize the need for out-of-sample testing and describes the walk-forward process.

But, modesty aside, my own "Quantitative Trading Systems", 2007, is unique in identifying the key issues involved in designing trading systems, with the desire that they will be profitable when traded.  It goes on to describe the combination of custom objective function, out-of-sample testing, and automated walk-forward testing which, in my opinion, is the only way to estimate what the results of actually trading the system are likely to be.  And, it includes practical examples illustrating how to design, test, and validate trading systems using methods that are reasonably rigorous.  The tutorial and reference, "Introduction to AmiBroker", 2008, works through a series of exercises illustrating the features of AmiBroker; beginning with installation and displaying the first chart and progressing through automated walk-forward testing.  The sequel, "Advanced AmiBroker", to be published about October 2009, will discuss and give AmiBroker code for the practical analysis of portfolios, risk, and position sizing -- all important features of realistic trading and trading management.

Why is there so little apparent interest?  Some possible reasons:
1.  Until AmiBroker, there has not been a retail-level trading system development platform that provided the capabilities needed.  Specifically, the abilities to define an objective function and perform automated walk-forward testing, and to work with portfolios as well as with individual issues.
2.  University courses in modeling and simulation that cover non-stationary time series with a focus on trading systems are rare (non-existant?).
3.  As soon as any attempt is made to be rigorous in modeling and validation technique, the mathematics involved put many people off.
4.  The popular press seems content with suggesting that backtesting is an adequate validation technique.  Since all backtesting results look good when backtesting is finished, it is easy to be disappointed and discouraged when out-of-sample testing shows poorer results.
5.  Coupling the fact that the rewards for developing profitable trading systems are so great with the fact that increased use of a profitable system reduces the profitability for everyone using it, people who have discovered good techniques tend to be reluctant to share them.
6.  There has been a lack of accessable educational material describing how a person might go about learning the techniques needed to be successful.

Thanks for listening,
Howard
www.blueowlpress.com  
  

On Mon, Feb 16, 2009 at 6:14 PM, brian_z111 <brian_z111@xxxxxxxxx> wrote:

> I know both David Aronson and Tim Masters. I like and recommend
>David's
> book, "Evidence-based Technical Analysis".

I find that DA and TM's public work is the most challenging, and up
to date material on system evaluation, going around i.e. for the
general trading community (don't know what is happening in academia).

I am benchmarking my ideas against theirs.

I was giving Tims paper a careful re-reading yesterday and went to
sleep (very quickly) with EBTA in my hand (no reflection on the book).

I don't think I will be going head to head with them any time soon,
for obvious reasons, but I will be noting my concerns, about MCP as a
tool for system evaluation, at the Zboard.

Naturally I will only do that in a naive way and won't be exhibiting
the mathematical rigor, and testing, that TM does in his paper
(others are welcome to do that, if they are interested, or refute my
arguments in writing anywhere they like ... I will upload any quality
posts mailed to me).

I am amazed at the low level of interest in the subject, by traders
in general, and also that 'we' haven't moved along very quickly,
since Pardo e.g. there's not a lot of quality books, on simulation
for trading, available.

(Haven't read the Scherer and Martin book, recommended by Patrick
yet).

Please let me know of any other hardcore authors worth referencing.


> Tim's paper on
> Monte Carlo makes some assumptions that I think are inappropriate
>for use
> when analyzing financial trading systems.

I am grateful that he made the effort and 'published' it.
It is the only definitive method I have found.

I also have some concerns about the method, albeit basic ones:

- it involves so many exceptions, to the extent that it is almost
impractical for general trading applications (admittedly TM has
provided a template that we can adjust to suit our own cirumstances)

- so far I am sceptical, about the possibility of mathematically
detecting survivor bias in optimization runs etc.

Note that I don't claim 100% understanding of MCP, or Whites Reality
Check, at this stage .... the fact that the MCP algorithm is written
in a foreign language doesn't make it easy for me (I haven't looked
at the C# version in our file section yet).


> Two, I feel that Monte Carlo analysis is of limited
> value when the trading system is completely deterministic.

I am not sure what you mean by 'deterministic' with regard to MCP.

Can you elaborate?

Re BiSim:

I feel it has some advantages over MCP and bootstrapping, at least as
an eductational tool and possibly in some limited trading
applications..... one of the advantages is that it is a convergence
simulation (it approaches the mean outcome quickly and without
massive effort) ... another is that it is very comfortable with
correlation (in fact I think other 'modellers' make hard work out of
handling it).

I hope to explore topics like that at the board.... obviously
developing rigorous signinficance tests is going to be a challenge,
if I get that far.

As I said, I am working live (I am not sure where it is going!), so
if my future 'research' shoots down my own theories so be it.

Thanks for the feedback.

brian+z


--- In amibroker@xxxxxxxxxxxxxxx, Howard B <howardbandy@xxx> wrote:
>
> Hi Brian --
>
> I know both David Aronson and Tim Masters. I like and recommend
David's
> book, "Evidence-based Technical Analysis". Readers of both David's
work and
> mine will find that David is even more conservative than I am
regarding
> interpretation of in-sample versus out-of-sample results. Tim's
paper on
> Monte Carlo makes some assumptions that I think are inappropriate
for use
> when analyzing financial trading systems. Two points in
particular. One, I
> feel that neither bootstrapping nor jacknifing should be used when
sampling
> financial time series. Two, I feel that Monte Carlo analysis is of
limited
> value when the trading system is completely deterministic. I'll
bring those
> up when I next talk with Tim.
>
> Thanks,
> Howard
>
> On Thu, Feb 12, 2009 at 4:54 PM, brian_z111 <brian_z111@xxx> wrote:
>
> > No rush.... I have been sitting on it for at least 2 years now.
> >
> > The full BinomialSimulation story won't be finished for months...
I
> > will only post about once a month.
> >
> > First I am going to track back to the beginning, for the benefit
of
> > non-mathematicians.
> >
> > Also, I will upload some stress test files, OR post images of the
key
> > graphs from those files, so interested parties don't need to
repeat
> > the massive simulations, for samples with bias and/or higher
> > dispersion, that I have already done.
> >
> > (Given your experience you would probably be best to sit back and
> > wait until I post the BS maths _expression_ ... it will be very easy
> > for you to test and critique my theory at that stage ... you can
> > leave the hack work to me).
> >
> > Note that it is a work in progress i.e. I am working 'live', warts
> > and all, and I might not finish it, or leave it on the net, (I
like
> > the Buddhist idea of 'pointing to the way' and demonstrating
> > impermanence).
> >
> > I probably won't 'advertise' here, in this forum, but BS posts
will
> > go onto the Zboard blog page so they can get picked up by RSS.
> >
> > The other pages at the site, which are mainly just resources etc,
> > won't be disseminated via RSS.
> >
> > FYI I think BS is a significant method compared to bootstrapping
and
> > MonteCarlo (considering their pros and cons) e.g. I disagree with
> > some of the assumptions of Timothy Masters, in his 2006 MCS
article
> > at Aronsons 'EvidenceBasedTechnicalAnalysisSite' site... I also
found
> > TM indecisive at some key points along the way.
> >
> > However, I am not going to follow the academic method of citing
> > others and criticising their work.
> >
> > I am very pleased you are looking at it.
> >
> > It has to stand up to the critique of informed mathematicians,
like
> > yourself (more so than other new ideas because I am a naive
> > mathematician and an intuitive rather than a trained
> > objectivist/academic).
> >
> > Around 20 people downloaded the file .... some of them would be
just
> > curious, or 'getting an education' (which are good things in
> > themselves) .... so at best there are only a few hard core
analysts
> > considering my 'thesis'.
> >
> > Pity QT isn't still around ... he was a very nice guy and very
good
> > on this stuff ;-)
> >
> > The Zboard site does allow for collaboration.
> >
> > If one or two self-managing people came along who wanted to add
> > something I could give them access ..... in that case the site
would
> > stay online for the benefit of future googling traders who are in
> > search of trading truths.
> >
> > Cheers and thanks for your interest ... it's a compliment.
> >
> > brian.
> >
> > --- In amibroker@xxxxxxxxxxxxxxx <amibroker%40yahoogroups.com>,
Howard B
> > <howardbandy@> wrote:
> > >
> > > Hi Brian --
> > >
> > > The zboard file worked fine.
> > >
> > > I have been snowed under with maintenance jobs the past week, so
> > it'll take
> > > me a couple of days to look at it.
> > >
> > > Thanks,
> > > Howard
> > >
> > > On Tue, Feb 10, 2009 at 1:06 AM, brian_z111 <brian_z111@> wrote:
> > >
> > > > Howard,
> > > >
> > > > I might move to MediaFire completely .. they are free
> > and 'permanent'
> > > > but the ads are terrible.
> > > >
> > > > With Rapidshare I will have to pay for some space to keep the
> > files
> > > > longer than 90 days but it is ad free.
> > > >
> > > > Haven't decided.
> > > >
> > > > Two files for you to try are at MF..... the PDF should give
you a
> > > > quick test of the download.
> > > >
> > > > Refer to Mirror Site links:
> > > >
> > > > http://zboard.wordpress.com/downloads/
> > > >
> > > > Future:
> > > >
> > > > - may upload the stress test files
> > > > - I have a math method in mind to bypass the number crunching
> > > > - the math formula would make it pretty easy to do in AFL
except
> > it
> > > > needs a trade array (workarounds possible with current AB
version
> > I
> > > > guess)
> > > > - part 2 files explore sample error/variance (if they are
going
> > > > somewhere I will post on that ... I recall I did find some
> > > > interesting relationships in error propogation but I haven't
> > looked
> > > > at it for a couple of years)
> > > >
> > > > Let me know if you can't download from mediafire
> > > >
> > > > OR if you can recommend a good filesharing site
> > > >
> > > > brian
> > > >
> > > >
> > > > --- In amibroker@xxxxxxxxxxxxxxx <amibroker%
40yahoogroups.com><amibroker%

> > 40yahoogroups.com>,
> > > > "brian_z111" <brian_z111@> wrote:
> > > > >
> > > > > The BS file is too big for Yahoo group files ... also it
would
> > clog
> > > > > up limited space.
> > > > >
> > > > > I thought about AB third party but I have to
download/maintain
> > > > third
> > > > > party software to FTP upload.... that annoys me somewhat (I
am a
> > > > very
> > > > > independent type).
> > > > >
> > > > > The Zboard/WordPress arrangement is a trial ... if it goes
> > smoothly
> > > > I
> > > > > will keep it going for a while.
> > > > >
> > > > > I am happy with the WordPress (limited filetype/space)
> > arrangement,
> > > > > with a file host for sharing.
> > > > >
> > > > > So, now I will consider other filesharing hosts.
> > > > >
> > > > > Anyone you can download from?
> > > > >
> > > > > I can put one somewhere else for you.
> > > > >
> > > > >
> > > > > Don't worry I will make sure you get one, way or another.
> > > > >
> > > > > Better to get another host though because there will be at
least
> > > > one
> > > > > more big file ..... if I keep going there might be plugins
one
> > day
> > > > so
> > > > > I need a universal host.
> > > > >
> > > > >
> > > > > brian_z111
> > > > >
> > > > > Zboard.wordpress.com
> > > > >
> > > > >
> > > > >
> > > > > --- In amibroker@xxxxxxxxxxxxxxx <amibroker%
40yahoogroups.com><amibroker%

> > 40yahoogroups.com>,
> > Howard B
> > > > <howardbandy@> wrote:
> > > > > >
> > > > > > Hi Brian --
> > > > > >
> > > > > > I use a Hughes satellite connection to the Internet. It
seems
> > > > that
> > > > > Hughes
> > > > > > appears to Rapidshare as a single user (which is always
over
> > its
> > > > > limit), so
> > > > > > I am never able to download a Rapidshare file. If
possible,
> > > > could
> > > > > you
> > > > > > upload the files to the Yahoo AmiBroker file section?
> > > > > >
> > > > > > Thanks,
> > > > > > Howard
> > > > > >
> > > > > >
> > > > > > On Sat, Feb 7, 2009 at 9:10 PM, brian_z111 <brian_z111@>
> > wrote:
> > > > > >
> > > > > > > I am using Rapidshare for file sharing.
> > > > > > >
> > > > > > > Free downloads are available but they are slower than
paid
> > > > > download
> > > > > > > and limited to 1 download per time ... wait a while and
you
> > can
> > > > > > > download again (still good value for my customers).
> > > > > > >
> > > > > > >
> > > >
http://rapidshare.com/files/195190948/BinomialMaster_ABVersion.xls
> > > > > > >
> > > > > > > A short ReadMe, to help understand the file, is at:
> > > > > > >
> > > > > > > http://zboard.wordpress.com/
> > > > > > >
> > > > > > > I can answer a few questions about the details in the
file
> > for a
> > > > > > > limited time (while my memory is fresh) .... post
> > questions, if
> > > > > any,
> > > > > > > via comments at the Zboard.
> > > > > > >
> > > > > > >
> > > > > > > --- In amibroker@xxxxxxxxxxxxxxx <amibroker%
40yahoogroups.com><amibroker%
> > 40yahoogroups.com><amibroker%
> > > > 40yahoogroups.com>,
> > > > > > > "brian_z111" <brian_z111@> wrote:
> > > > > > > >
> > > > > > > > File limits prevented me uploading the
BinomialSimulation
> > file
> > > > > (s)
> > > > > > > to
> > > > > > > > this group ... 20MB per file. I will post links to at
> > least
> > > > one
> > > > > > > > example, at the following temporary site, sometime
this
> > week:
> > > > > > > >
> > > > > > > > http://zboard.wordpress.com/
> > > > > > > >
> > > > > > > > I will post some basic notes afterall because the
task of
> > > > > following
> > > > > > > > the Excel sheets would be beyond anyone without them.
> > > > > > > >
> > > > > > > > The site might live on for a while after that.
> > > > > > > >
> > > > > > > >
> > > > > > > > --- In amibroker@xxxxxxxxxxxxxxx <amibroker%
40yahoogroups.com><amibroker%
> > 40yahoogroups.com><amibroker%
> >
> > > > 40yahoogroups.com>,
> > > > > > > "brian_z111" <brian_z111@> wrote:
> > > > > > > > >
> > > > > > > > > I decided to post the Binomial Simulation files a
few
> > days
> > > > > > > ago ...
> > > > > > > > I
> > > > > > > > > am not going to announce the upload so this post is
the
> > > > > > > discussion
> > > > > > > > > link for them (one or more files will appear at some
> > stage).
> > > > > > > > >
> > > > > > > > > FTR They do predict the eq dist quite well, for
biased
> > and
> > > > > none
> > > > > > > > > biased 'coins' but there is one thing about them
that
> > does
> > > > > > > concern
> > > > > > > > > me ... I referenced the same synthetic trade series
to
> > make
> > > > > the
> > > > > > > > > binomial distribution and to create the synthetic eq
> > > > > curves ...
> > > > > > > > that
> > > > > > > > > seems a bit incestuous in some ways.
> > > > > > > > >
> > > > > > > > > On the other hand they could be full of incorrect
math
> > > > > > > assumptions
> > > > > > > > > cos I got the math off Wikipedia!
> > > > > > > > >
> > > > > > > > > Guru Brian ;-)
> > > > > > > > >
> > > > > > > > >
> > > > > > > > > --- In amibroker@xxxxxxxxxxxxxxx<amibroker%
40yahoogroups.com><amibroker%
> > 40yahoogroups.com><amibroker%
> >
> > > > > 40yahoogroups.com>,
> > > > > > > "brian_z111" <brian_z111@>
> > > > > > > wrote:
> > > > > > > > > >
> > > > > > > > > >
> > > > > > > > > > > This is a valid model as long as stationarity
> > holds ...
> > > > I
> > > > > > > have
> > > > > > > > > > > simulated random trading 'systems' and
predicted the
> > > > > outcome
> > > > > > > by
> > > > > > > > > > using
> > > > > > > > > > > binomial probability, that references a
frequency
> > > > > > > distribution
> > > > > > > > of
> > > > > > > > > > the
> > > > > > > > > > > randomly generated trades, and it predicted the
> > actual
> > > > > equity
> > > > > > > > > > > distributions extremely well (a lognormal dist
> > appears
> > > > at
> > > > > > > very
> > > > > > > > > high
> > > > > > > > > > > N's).
> > > > > > > > > >
> > > > > > > > > >
> > > > > > > > > > More precisely, I have simulated trade series,
using
> > the
> > > > > RNG in
> > > > > > > > > > Excel, for random walks (50/50 systems) and biased
> > > > systems,
> > > > > > > with
> > > > > > > > > > normally distributed trade series (I used
> > > > > CentralLimitThereom
> > > > > > > to
> > > > > > > > > > create NormDists from the uniform output of the
> > generator.
> > > > > > > > > >
> > > > > > > > > > I simulated equity curves, using the synthetic
trades,
> > > > and
> > > > > at
> > > > > > > the
> > > > > > > > > > same time used BinomialProb to model the predicted
> > > > > distribution
> > > > > > > > of
> > > > > > > > > > the eq curves (I imagined I was tossing a coin
with
> > > > variable
> > > > > > > > values
> > > > > > > > > > for heads and tails ... of course in trading we
can
> > win
> > > > > lose or
> > > > > > > > > draw
> > > > > > > > > > whereas in my model we can only win or lose).
> > > > > > > > > >
> > > > > > > > > > You might like to see the files?
> > > > > > > > > >
> > > > > > > > > > I am bored with that topic.
> > > > > > > > > >
> > > > > > > > > > I am not a mathematician ... it might be a load
of old
> > > > > rubbish
> > > > > > > > for
> > > > > > > > > > all I know.
> > > > > > > > > >
> > > > > > > > > > As our discussion shows .. we can't get any
> > statistical
> > > > > > > certainty
> > > > > > > > > > anywhere in trading ... only approximations and
> > > > > probabilties.
> > > > > > > > > >
> > > > > > > > > > It is just another approximation, like MCS and
> > involves
> > > > > massive
> > > > > > > > > > number crunching.
> > > > > > > > > >
> > > > > > > > > > I didn't finish it because I wanted a quick and
dirty
> > > > > method.
> > > > > > > > > >
> > > > > > > > > > The files are rough as old bags.
> > > > > > > > > >
> > > > > > > > > > I didn't make notes so even I have a hard time
> > following
> > > > the
> > > > > > > > > > logic ... I had a look at them the other day I
had to
> > > > start
> > > > > > > > tracing
> > > > > > > > > > the formulas in the cells to see how I had done
it.
> > > > > > > > > >
> > > > > > > > > > I'll post some of them in the file section one day
> > (Howard
> > > > > > > > collects
> > > > > > > > > > trading things).
> > > > > > > > > >
> > > > > > > > > > I won't scrub them up though ... take them or
leave
> > > > them ...
> > > > > > > > sorry
> > > > > > > > > no
> > > > > > > > > > questions or explanations (anyway Howard and other
> > maths
> > > > > people
> > > > > > > > > know
> > > > > > > > > > how to do that stuff).
> > > > > > > > > >
> > > > > > > > > >
> > > > > > > > > > --- In amibroker@xxxxxxxxxxxxxxx<amibroker%
40yahoogroups.com><amibroker%
> > 40yahoogroups.com><amibroker%
> >
> > > > > 40yahoogroups.com>,
> > > > > > > "brian_z111" <brian_z111@>
> > > > > > > > wrote:
> > > > > > > > > > >
> > > > > > > > > > > Gidday Mate,
> > > > > > > > > > >
> > > > > > > > > > > I wasn't planning on posting again today as I am
> > going
> > > > > away
> > > > > > > for
> > > > > > > > a
> > > > > > > > > > few
> > > > > > > > > > > days ..... a good question though so I couldn't
> > resist.
> > > > > > > > > > >
> > > > > > > > > > >
> > > > > > > > > > > I did notice Fred's comment on the priority he
> > places on
> > > > > > > > > > sensitivity
> > > > > > > > > > > analysis.
> > > > > > > > > > >
> > > > > > > > > > > He has made the comment before and I came to
that
> > view
> > > > > > > > > > independently
> > > > > > > > > > > a way back anyway (Howard's random noise test is
> > another
> > > > > > > > > > interesting
> > > > > > > > > > > idea for single sample analysis).
> > > > > > > > > > >
> > > > > > > > > > > I also recall that he doesn't believe
scrambling the
> > > > > order of
> > > > > > > > the
> > > > > > > > > > > trades provides any meaningful feedback.
> > > > > > > > > > >
> > > > > > > > > > > That isn't a reason for me not to reach my own
> > > > > conclusions.
> > > > > > > > > > >
> > > > > > > > > > > Fred has also talked about small N retesting
(walk
> > > > > forward),
> > > > > > > > and
> > > > > > > > > > > adjusting his system rules, on a short term
basis,
> > so
> > > > > while I
> > > > > > > > am
> > > > > > > > > > not
> > > > > > > > > > > keen on the idea I am keeping an open mind on
the
> > > > subject.
> > > > > > > > > > >
> > > > > > > > > > >
> > > > > > > > > > >
> > > > > > > > > > > > This is the second time in the >past few
> > > > > > > > > > > > days that you seem to have equated
> > trading/backtesting
> > > > > > > system
> > > > > > > > > > > >outcomes
> > > > > > > > > > > > to a random series of coin flip outcomes
(random
> > > > binary
> > > > > > > > > > occurances).
> > > > > > > > > > > >
> > > > > > > > > > > > Serious question... what is your point? What
is
> > the
> > > > > > > > relevence
> > > > > > > > > os
> > > > > > > > > > > >the
> > > > > > > > > > > > "Coin Flip" metaphor where trading systems is
> > > > concerned?
> > > > > > > > > > >
> > > > > > > > > > > Well, developers are selling software
specifically
> > > > > designed
> > > > > > > for
> > > > > > > > > > > performing MSC for trading analysis and at
least one
> > > > guy
> > > > > has
> > > > > > > > > > written
> > > > > > > > > > > a book on the subject.
> > > > > > > > > > >
> > > > > > > > > > > In both software packages, that I have some
> > familiarity
> > > > > with,
> > > > > > > > > their
> > > > > > > > > > > model assumes stationarity, and independency
i.e.
> > their
> > > > > model
> > > > > > > > > > treats
> > > > > > > > > > > the data as if it is the outcome of a coin toss
with
> > > > > variable
> > > > > > > > > > values
> > > > > > > > > > > on the +- side of the coin.
> > > > > > > > > > >
> > > > > > > > > > > This is a valid model as long as stationarity
> > holds ...
> > > > I
> > > > > > > have
> > > > > > > > > > > simulated random trading 'systems' and
predicted the
> > > > > outcome
> > > > > > > by
> > > > > > > > > > using
> > > > > > > > > > > binomial probability, that references a
frequency
> > > > > > > distribution
> > > > > > > > of
> > > > > > > > > > the
> > > > > > > > > > > randomly generated trades, and it predicted the
> > actual
> > > > > equity
> > > > > > > > > > > distributions extremely well (a lognormal dist
> > appears
> > > > at
> > > > > > > very
> > > > > > > > > high
> > > > > > > > > > > N's).
> > > > > > > > > > >
> > > > > > > > > > > The value, to me in that model, is that it is a
> > > > training
> > > > > tool
> > > > > > > > > that
> > > > > > > > > > > conditioned me to accept variance as 'normal'
and
> > if the
> > > > > > > market
> > > > > > > > > is
> > > > > > > > > > > stationary then it would have direct relevance
to
> > > > > > > trading.....
> > > > > > > > > the
> > > > > > > > > > > worst case outcome would be that I could incur
> > losses,
> > > > > with a
> > > > > > > > > > > probability as indicated by the Cumulative
> > Distrubution
> > > > > > > > Function
> > > > > > > > > > for
> > > > > > > > > > > the possible equity outcomes (simulation is one
way
> > for
> > > > > non -
> > > > > > > > > > > mathematicians to calc this and view it in a
chart).
> > > > > > > > > > >
> > > > > > > > > > >
> > > > > > > > > > > Ask yourself ....
> > > > > > > > > > >
> > > > > > > > > > > afer you have conducted a successful OOS, and
> > collated
> > > > the
> > > > > > > > trade
> > > > > > > > > > > sample, when you start to trade it do you
expect:
> > > > > > > > > > >
> > > > > > > > > > > - all trades to be the same, or similar, and
occur
> > with
> > > > > the
> > > > > > > > same
> > > > > > > > > > > frequency (TradeSim),
> > > > > > > > > > > - all trades to be the same, or similar, and
have
> > > > > variations
> > > > > > > in
> > > > > > > > > the
> > > > > > > > > > > frequency (MSA),
> > > > > > > > > > > - something else?
> > > > > > > > > > >
> > > > > > > > > > > Trading, however, is not a coin toss.
> > > > > > > > > > >
> > > > > > > > > > > It is more like a sample generator that produces
> > trades
> > > > > as a
> > > > > > > > > result
> > > > > > > > > > > of presenting dynamic data to the system
(filter).
> > > > > > > > > > >
> > > > > > > > > > > To what extent could a 'real life' trading
system
> > > > emulate
> > > > > a
> > > > > > > > coin
> > > > > > > > > > > toss, with variable values ... how could that
come
> > > > about?
> > > > > > > > > > >
> > > > > > > > > > > (interesting that the very functional optF
formula
> > came
> > > > > about
> > > > > > > > as
> > > > > > > > > > the
> > > > > > > > > > > variable value coin toss staking formula).
> > > > > > > > > > >
> > > > > > > > > > > Is it possible or not?
> > > > > > > > > > >
> > > > > > > > > > > A lot of people seem to think it is, judging by
> > their
> > > > > books
> > > > > > > and
> > > > > > > > > > > software.
> > > > > > > > > > >
> > > > > > > > > > > Presumably, when the underlying data changes,
the
> > sample
> > > > > > > > profile
> > > > > > > > > > > (mean, StDev etc) can change and we end up with
a
> > > > better
> > > > > or
> > > > > > > > worse
> > > > > > > > > > > outcome than anticipated by the OOS.
> > > > > > > > > > >
> > > > > > > > > > > So, does the non-stationary behaviour of the
markets
> > > > > > > invalidate
> > > > > > > > > the
> > > > > > > > > > > coin toss model?
> > > > > > > > > > >
> > > > > > > > > > > That is the ineresting question, and I don't
know
> > the
> > > > > answer
> > > > > > > to
> > > > > > > > > it,
> > > > > > > > > > > or even if there is a definite answer.
> > > > > > > > > > >
> > > > > > > > > > > I was hopeful that people would pick up on that
key
> > > > point
> > > > > and
> > > > > > > > > shed
> > > > > > > > > > > some light on the subject.
> > > > > > > > > > >
> > > > > > > > > > > I know, from my long hours of simulating random
> > data,
> > > > what
> > > > > > > > random
> > > > > > > > > > > behaviour looks like when I see it.
> > > > > > > > > > >
> > > > > > > > > > > Clearly the markets have a certain amount of
random
> > > > > behaviour.
> > > > > > > > > > >
> > > > > > > > > > > Howard commented somewhere, or another, that
there
> > is a
> > > > > > > certain
> > > > > > > > > > > amount of randomness in the market (I can't
recall
> > the
> > > > > method
> > > > > > > > he
> > > > > > > > > > used
> > > > > > > > > > > to measure it).
> > > > > > > > > > >
> > > > > > > > > > > It is quite easy to observe if data has any
random
> > > > > qualities,
> > > > > > > > > > > especially if we measure the core attributes
(50/50
> > > > heads
> > > > > and
> > > > > > > > > tails
> > > > > > > > > > > and its persistence into 2,3,4 heads in a row
etc).
> > > > > > > > > > >
> > > > > > > > > > > Once again I ask you to consider:
> > > > > > > > > > >
> > > > > > > > > > > if I measure the S&P500 index, on close, and it
> > goes up
> > > > > > > approx
> > > > > > > > 50
> > > > > > > > > > and
> > > > > > > > > > > down approx 50 (+- variance that is typical of a
> > random
> > > > > > > > binomial
> > > > > > > > > > > event) and the subsequent second head or tail
follow
> > > > with
> > > > > 0.5
> > > > > > > > > prob
> > > > > > > > > > > etc I am justified in considering it top be a
pseudo
> > > > > random
> > > > > > > > > > binomail
> > > > > > > > > > > event?
> > > > > > > > > > >
> > > > > > > > > > > I have done quick and dirty measurements, and
> > accurate
> > > > > > > > > > measurements,
> > > > > > > > > > > on dependency (or on its inverse, which is
> > > > independency)
> > > > > and
> > > > > > > > find
> > > > > > > > > > > that there is a good deal of independency in the
> > > > markets
> > > > > (I
> > > > > > > > > posted
> > > > > > > > > > > some q&d code to measure that last week).
> > > > > > > > > > >
> > > > > > > > > > > I have speculated before, on the point, that the
> > > > rational
> > > > > > > > market
> > > > > > > > > is
> > > > > > > > > > > the market that follows fundamental value, which
> > tends
> > > > to
> > > > > be
> > > > > > > >=
> > > > > > > > > the
> > > > > > > > > > > yearly (macro) timeframe, and, everything else
is
> > the
> > > > > > > > irrational
> > > > > > > > > > > market.
> > > > > > > > > > >
> > > > > > > > > > > Consider an intraday market ... what is rational
> > about
> > > > the
> > > > > > > > price
> > > > > > > > > > > movement during any given part of the day?
> > > > > > > > > > >
> > > > > > > > > > > - Draw a trend line on the chart .. we will
assume
> > that
> > > > we
> > > > > > > know
> > > > > > > > > > what
> > > > > > > > > > > a trend is for this exercise, although that is a
> > > > debatable
> > > > > > > > point.
> > > > > > > > > > >
> > > > > > > > > > > - The trend, a straight line, is rational (it is
> > > > perfectly
> > > > > > > > > > following
> > > > > > > > > > > fundamental value).... it is 2007 and it is
up ;-)
> > > > > > > > > > >
> > > > > > > > > > > - All of the ups and downs that occur around it
are
> > > > > > > irrational
> > > > > > > > > > > (bucking the trend).
> > > > > > > > > > >
> > > > > > > > > > > - The trend line goes under the pivot lows.
> > > > > > > > > > >
> > > > > > > > > > > - Your system buys at the pivot lows and sells
at =
> > = 2
> > > > > StDev
> > > > > > > > > above
> > > > > > > > > > > the trend line.
> > > > > > > > > > >
> > > > > > > > > > > - Place a stop under the trend line at - 1
stDev.
> > > > > > > > > > >
> > > > > > > > > > > - Assume no commission and no slippage.
> > > > > > > > > > >
> > > > > > > > > > > - Your payoff ratio is 2/1
> > > > > > > > > > >
> > > > > > > > > > > - assume there is no variance in volatility so
the
> > PR
> > > > is a
> > > > > > > > > constant
> > > > > > > > > > > value
> > > > > > > > > > >
> > > > > > > > > > > - the win/loss ratio is determined by the random
> > > > > meandering
> > > > > > > of
> > > > > > > > > the
> > > > > > > > > > > irrational price movements up and down.
> > > > > > > > > > >
> > > > > > > > > > > Note they are irrational because people are
buying
> > and
> > > > > > > selling
> > > > > > > > at
> > > > > > > > > > the
> > > > > > > > > > > wrong time and for the wrong reasons - if they
were
> > > > > rational
> > > > > > > > they
> > > > > > > > > > > would only be buying selling as fundamental
values
> > > > change.
> > > > > > > > > > >
> > > > > > > > > > > - the trade series produced would look exactly
that
> > that
> > > > > > > > produced
> > > > > > > > > > by
> > > > > > > > > > > a coin tossed with +2, -1 value on it.
> > > > > > > > > > >
> > > > > > > > > > > Now, you have tested this system, OOS, and it
is a
> > > > winner.
> > > > > > > > > > >
> > > > > > > > > > > What chance for stationarity when you trade
live?
> > > > > > > > > > >
> > > > > > > > > > > If the trend continues there is a very good
chance
> > that
> > > > > the
> > > > > > > > > random
> > > > > > > > > > > emualator (system meeting dynamic data) will
> > continue to
> > > > > > > > perform
> > > > > > > > > > like
> > > > > > > > > > > a biased coin +- variance i.e. the payoff ratio
> > can't
> > > > > change
> > > > > > > > but
> > > > > > > > > > the
> > > > > > > > > > > W/L will (it always does when I toss a coin).
> > > > > > > > > > >
> > > > > > > > > > > If the trend changes your winning model will be
more
> > > > > likely
> > > > > > > to
> > > > > > > > > bust.
> > > > > > > > > > >
> > > > > > > > > > > That could be the reason Fred, and others, like
to
> > > > > > > continually
> > > > > > > > > > retest.
> > > > > > > > > > >
> > > > > > > > > > > I have another approach to getting around this
> > problem
> > > > > (this
> > > > > > > is
> > > > > > > > > > > actually the real point of my posts) ...
> > > > > > > > > > >
> > > > > > > > > > > ..... to accomodate non-stationarity either
adjust
> > > > > quickly OR
> > > > > > > > use
> > > > > > > > > a
> > > > > > > > > > > dimensionless model e.g. don't believe in
trends and
> > > > then
> > > > > you
> > > > > > > > > can't
> > > > > > > > > > > be on the wrong side of them.
> > > > > > > > > > >
> > > > > > > > > > >
> > > > > > > > > > >
> > > > > > > > > > > However, that is only speculation.
> > > > > > > > > > >
> > > > > > > > > > > What do you think?
> > > > > > > > > > >
> > > > > > > > > > >
> > > > > > > > > > > Again ... what is the relevance of coin tosses
to
> > > > trading
> > > > > IMO:
> > > > > > > > > > >
> > > > > > > > > > >
> > > > > > > > > > > - wonderful training tool
> > > > > > > > > > > - a good OOS can not predict exactly what the
> > outcome
> > > > of
> > > > > live
> > > > > > > > > > trading
> > > > > > > > > > > will be (subject to nonstationarity) and
neither can
> > > > > > > simulation
> > > > > > > > > > (coin
> > > > > > > > > > > tossing) but it gives a good approximation of
the
> > > > > > > possibilities
> > > > > > > > > > (also
> > > > > > > > > > > subject to non-stationarity).
> > > > > > > > > > >
> > > > > > > > > > > As a quid pro quo .....
> > > > > > > > > > >
> > > > > > > > > > > ..... if you, or anyone else, can give me any
> > > > explanation
> > > > > > > > and/or
> > > > > > > > > > > proof that the coin toss metaphor has no
relevance
> > to
> > > > > trading
> > > > > > > I
> > > > > > > > > > would
> > > > > > > > > > > be delighted.
> > > > > > > > > > >
> > > > > > > > > > >
> > > > > > > > > > > Anyway, I think Patrick already answered the
> > question,
> > > > or
> > > > > > > told
> > > > > > > > us
> > > > > > > > > > > where to find it.
> > > > > > > > > > >
> > > > > > > > > > > Good luck with your trading.
> > > > > > > > > > >
> > > > > > > > > > > brian_zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz
> > > > > > > > > > >
> > > > > > > > > > >
> > > > > > > > > > > --- In amibroker@xxxxxxxxxxxxxxx<amibroker%
40yahoogroups.com>
> > <amibroker%
> > 40yahoogroups.com><amibroker%
> >
> > > > > 40yahoogroups.com>,
> > > > > > > "Phsst" <phsst@> wrote:
> > > > > > > > > > > >
> > > > > > > > > > > > Hello Brian,
> > > > > > > > > > > >
> > > > > > > > > > > > Thanks for the mention in your New Years
post. I
> > felt
> > > > > > > > humbled
> > > > > > > > > to
> > > > > > > > > > > be in
> > > > > > > > > > > > the same honerable mention list as Fred (He
is a
> > very
> > > > > smart
> > > > > > > > > Dude
> > > > > > > > > > (no
> > > > > > > > > > > > kidding!)) It took me a while (some years
back) to
> > > > > figure
> > > > > > > out
> > > > > > > > > > what a
> > > > > > > > > > > > smart guy Fred really is. I've since learned
that
> > > > when
> > > > > Fred
> > > > > > > > > > speaks,
> > > > > > > > > > > it
> > > > > > > > > > > > pays to think and be silent for a good long
while
> > > > before
> > > > > > > > > drawing
> > > > > > > > > > any
> > > > > > > > > > > > conclusions.
> > > > > > > > > > > >
> > > > > > > > > > > > To your "crystal clear" point... This is the
> > second
> > > > > time in
> > > > > > > > the
> > > > > > > > > > > past few
> > > > > > > > > > > > days that you seem to have equated
> > trading/backtesting
> > > > > > > system
> > > > > > > > > > > outcomes
> > > > > > > > > > > > to a random series of coin flip outcomes
(random
> > > > binary
> > > > > > > > > > occurances).
> > > > > > > > > > > >
> > > > > > > > > > > > Serious question... what is your point? What
is
> > the
> > > > > > > > relevence
> > > > > > > > > os
> > > > > > > > > > > the
> > > > > > > > > > > > "Coin Flip" metaphor where trading systems is
> > > > concerned?
> > > > > > > > What
> > > > > > > > > am
> > > > > > > > > > I
> > > > > > > > > > > > missing?
> > > > > > > > > > > >
> > > > > > > > > > > > Your Bud... Phsst
> > > > > > > > > > > >
> > > > > > > > > > > >
> > > > > > > > > > > >
> > > > > > > > > > > > This is the second time
> > > > > > > > > > > > --- In amibroker@xxxxxxxxxxxxxxx<amibroker%
40yahoogroups.com>
> > <amibroker%
> > 40yahoogroups.com><amibroker%
> >
> > > > > 40yahoogroups.com>,
> > > > > > > "brian_z111"
> > > > > > > <brian_z111@>
> > > > > > > > > > wrote:
> > > > > > > > > > > > >
> > > > > > > > > > > > > To be chrystal clear about my hypothesis:
> > > > > > > > > > > > >
> > > > > > > > > > > > >
> > > > > > > > > > > > > We are trying to design a system that
produces
> > the
> > > > > same
> > > > > > > set
> > > > > > > > of
> > > > > > > > > > > > > trades, in the future, as it has in the
past i.e
> > > > > trades
> > > > > > > and
> > > > > > > > > not
> > > > > > > > > > > > > combinations of trades.
> > > > > > > > > > > > >
> > > > > > > > > > > > > If a solid gold coin, minted by the US
treasury,
> > > > with
> > > > > a
> > > > > > > > head
> > > > > > > > > > and a
> > > > > > > > > > > > > tail clearly stamped on each side, and only
two
> > > > > values +1
> > > > > > > > or -
> > > > > > > > > 1
> > > > > > > > > > > can't
> > > > > > > > > > > > > reproduce two equity curves that look the
same,
> > > > after
> > > > > N
> > > > > > > > > tosses,
> > > > > > > > > > > how
> > > > > > > > > > > > > can we expect a trading system to do that
when
> > it
> > > > has
> > > > > a
> > > > > > > > range
> > > > > > > > > of
> > > > > > > > > > > > > possible values?
> > > > > > > > > > > > >
> > > > > > > > > > > > > AND it doesn't get any better as N
increases.
> > > > > > > > > > > > >
> > > > > > > > > > > > > Put your time and effort into maximising the
> > > > STABILITY
> > > > > > > > > > > > > (predictability, boundness) of the trade
> > set 'with
> > > > an
> > > > > > > edge'
> > > > > > > > > > THEN
> > > > > > > > > > > use
> > > > > > > > > > > > > MM to optimise the equity outcome the system
> > > > produces
> > > > > > > > > (optimise
> > > > > > > > > > ==
> > > > > > > > > > > > > your definition e.g. max return, min risk or
> > > > > whatever).
> > > > > > > > > > > > >
> > > > > > > > > > > > >
> > > > > > > > > > > > >
> > > > > > > > > > > > >
> > > > > > > > > > > > > --- In amibroker@xxxxxxxxxxxxxxx<amibroker%
40yahoogroups.com>
> > <amibroker%
> > 40yahoogroups.com><amibroker%
> >
> > > > > 40yahoogroups.com>,
> > > > > > > "brian_z111"
> > > > > > > brian_z111@
> > > > > > > > > > wrote:
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Howard,
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Thanks for your post.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > A very well written article.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Some contrary comment (first referencing
some
> > of
> > > > > your
> > > > > > > > > points
> > > > > > > > > > and
> > > > > > > > > > > > > > then, later, some comments of my own):
> > > > > > > > > > > > > >
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > > By trying many
> > > > > > > > > > > > > > > combinations of logic and parameter
values,
> > we
> > > > > will
> > > > > > > > > > eventually
> > > > > > > > > > > > > find
> > > > > > > > > > > > > > >a system that is profitable for the date
> > range
> > > > > > > analyzed.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > You are assuming that all successful long
term
> > > > > traders
> > > > > > > > > > arrived
> > > > > > > > > > > at
> > > > > > > > > > > > > > their system(s) by using this approach ...
> > perhaps
> > > > > > > there
> > > > > > > > > are
> > > > > > > > > > > > > systems
> > > > > > > > > > > > > > out there that have no optimiseable
parameters
> > > > and
> > > > > only
> > > > > > > > one
> > > > > > > > > > > > > > underlying logic.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > If so they are likely be based on primal
> > market
> > > > > > > behaviour
> > > > > > > > > and
> > > > > > > > > > > > > > therefore persistent across markets and
time
> > i.e
> > > > > they
> > > > > > > > would
> > > > > > > > > > > have to
> > > > > > > > > > > > > > be systems based on market characteristics
> > that
> > > > are
> > > > > > > > > relatively
> > > > > > > > > > > > > > stationary.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > >
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > > testing the
> > > > > > > > > > > > > > > profitability of a trading system that
was
> > > > > developed
> > > > > > > > > using
> > > > > > > > > > > recent
> > > > > > > > > > > > > > >data
> > > > > > > > > > > > > > > on older data is guaranteed to over-
> > estimate the
> > > > > > > > > > > profitability of
> > > > > > > > > > > > > > the
> > > > > > > > > > > > > > > trading system.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > You know that in science
(philosophy/logic) it
> > > > only
> > > > > > > takes
> > > > > > > > > one
> > > > > > > > > > > > > > refutation to dethrone the current ruling
> > > > > hypothesis ...
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > if a long system, developed on the last 12
> > months
> > > > of
> > > > > > > data
> > > > > > > > > > (when
> > > > > > > > > > > the
> > > > > > > > > > > > > > market was experiencing a bear riot) is
then
> > > > tested
> > > > > OOS
> > > > > > > > on
> > > > > > > > > the
> > > > > > > > > > > > > prior
> > > > > > > > > > > > > > years data it will outperform the in
sample
> > tests
> > > > > (OOS
> > > > > > > > > would
> > > > > > > > > > be
> > > > > > > > > > > > > > conducted on bull market data).
> > > > > > > > > > > > > >
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > > There is very little reason to expect
that
> > > > future
> > > > > > > > > behavior
> > > > > > > > > > and
> > > > > > > > > > > > > > > profitability of well known trading
systems
> > > > will
> > > > > be
> > > > > > > the
> > > > > > > > > > same
> > > > > > > > > > > as
> > > > > > > > > > > > > past
> > > > > > > > > > > > > > > behavior.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Do we have any empirical evidence of this?
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > First we would have to have an agreed
> > definition
> > > > > > > of 'well
> > > > > > > > > > > known',
> > > > > > > > > > > > > > make a list of the systems, and then
perform
> > > > massive
> > > > > > > > > testing.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > To scrupulously prevent any bias creeping
> > testing
> > > > > would
> > > > > > > > > have
> > > > > > > > > > to
> > > > > > > > > > > be
> > > > > > > > > > > > > > conducted live, and not on historical
data.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > We only know that they were
successful 'in the
> > > > > past' by
> > > > > > > > IS
> > > > > > > > > > > testing,
> > > > > > > > > > > > > > or by claim.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Do we have any, or many, certified
performance
> > > > > records
> > > > > > > > > > provided
> > > > > > > > > > > by
> > > > > > > > > > > > > > traders who claim to have had success with
> > > > > those 'well
> > > > > > > > > known'
> > > > > > > > > > > > > systems.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > > Statistics gathered from in-sample
results
> > have
> > > > > > > > > > > > > > > no relationship to statistics that will
be
> > > > > gathered
> > > > > > > > from
> > > > > > > > > > > trading.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Not, so.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > They have every bearing on the stats
gathered
> > in
> > > > > > > trading
> > > > > > > > > > because
> > > > > > > > > > > > > only
> > > > > > > > > > > > > > systems with good IS performance make it
to
> > the
> > > > OS,
> > > > > or
> > > > > > > > live
> > > > > > > > > > > > > trading,
> > > > > > > > > > > > > > phase.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > OOS testing is only proceeded with
because the
> > > > > analyst
> > > > > > > > has
> > > > > > > > > > every
> > > > > > > > > > > > > > expectation, or hope, that the good IS
stats
> > will
> > > > be
> > > > > > > > > > reproduced
> > > > > > > > > > > OOS.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > In fact it is the relative performance
between
> > > > the
> > > > > IS
> > > > > > > and
> > > > > > > > > OOS
> > > > > > > > > > > stats
> > > > > > > > > > > > > > the encourages us to proceed or abort.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > >
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Re trading the edge erodes the edge:
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > It is an assumption that all players are
> > trading
> > > > > > > > > systems ...
> > > > > > > > > > > many
> > > > > > > > > > > > > are
> > > > > > > > > > > > > > not, in fact the vast majority are not....
> > those
> > > > who
> > > > > > > > aren't
> > > > > > > > > > > control
> > > > > > > > > > > > > > vastly greater sums of money than those
who
> > do.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > It is an assumption that all wins erode
the
> > > > > system ...
> > > > > > > > they
> > > > > > > > > > > could
> > > > > > > > > > > > > be
> > > > > > > > > > > > > > just lucky wins that the trader can't
exploit
> > long
> > > > > > > term,
> > > > > > > > or
> > > > > > > > > > > > > > successful wins that the trader doesn't
> > sustain
> > > > e.g
> > > > > > > they
> > > > > > > > > > might
> > > > > > > > > > > not
> > > > > > > > > > > > > > have the capital, use the correct staking
or
> > > > > maintain
> > > > > > > > self-
> > > > > > > > > > > > > discipline
> > > > > > > > > > > > > > in the future.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Only a very small percentage of traders
are
> > > > > successful,
> > > > > > > > and
> > > > > > > > > > > hence
> > > > > > > > > > > > > > trading a successful system ... every one
else
> > > > who
> > > > > is
> > > > > > > > > trading
> > > > > > > > > > is
> > > > > > > > > > > > > just
> > > > > > > > > > > > > > making noise.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > There are millions of system permutations,
> > > > > instruments,
> > > > > > > > > > markets,
> > > > > > > > > > > > > > staking systems etc ..... how many
successful
> > > > > traders
> > > > > > > > would
> > > > > > > > > > it
> > > > > > > > > > > take
> > > > > > > > > > > > > > to exahaust all of the successful
> > permutations?
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > > The follow-on point, which relates to
Monte
> > > > Carlo
> > > > > > > > > analysis,
> > > > > > > > > > is
> > > > > > > > > > > > > that
> > > > > > > > > > > > > > > rearranging the in-sample trades gives
no
> > > > insight
> > > > > > > into
> > > > > > > > > the
> > > > > > > > > > > future
> > > > > > > > > > > > > > > characteristics of the system. Yes, you
can
> > see
> > > > > the
> > > > > > > > > effect
> > > > > > > > > > of
> > > > > > > > > > > > > taking
> > > > > > > > > > > > > > > the trades in different orders. But why
> > bother?
> > > > > They
> > > > > > > > are
> > > > > > > > > > still
> > > > > > > > > > > > > > > in-sample results and still have no
value.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > If you are engineering an F1 racing car
there
> > is
> > > > > only
> > > > > > > > track
> > > > > > > > > > > > > > testing/simulation (99.9 of the time) and
> > racing
> > > > > > > > > performance
> > > > > > > > > > > (1% of
> > > > > > > > > > > > > > the time).
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > The more information you gather off the
track
> > the
> > > > > more
> > > > > > > > > likely
> > > > > > > > > > > you
> > > > > > > > > > > > > are
> > > > > > > > > > > > > > to perform on the track OR know what to
adjust
> > > > and
> > > > > when
> > > > > > > > to
> > > > > > > > > > > adjust
> > > > > > > > > > > > > it
> > > > > > > > > > > > > > if performance doesn't meet expectations.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Do you know of any F1 teams that don't
> > > > > test/simulate?
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Do you know of any F1 teams that only
> > > > test/simulate
> > > > > > > one,
> > > > > > > > or
> > > > > > > > > > > > > limited,
> > > > > > > > > > > > > > metrics?
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > What is testing if not 'massive
examination of
> > > > what-
> > > > > if
> > > > > > > > > > > scenarios'?
> > > > > > > > > > > > > >
> > > > > > > > > > > > > >
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Re MonteCarlo and stationarity
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > I haven't studied the subject in depth.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Mainly it is has been used outside of
trading
> > and
> > > > in
> > > > > > > > > > different
> > > > > > > > > > > ways
> > > > > > > > > > > > > > to the ways that traders use it ....
possibly
> > it
> > > > > would
> > > > > > > > be
> > > > > > > > > > best
> > > > > > > > > > > to
> > > > > > > > > > > > > > limit trading discussion to 'trading
> > simulation'
> > > > and
> > > > > > > drop
> > > > > > > > > the
> > > > > > > > > > MC
> > > > > > > > > > > > > part
> > > > > > > > > > > > > > of the name.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > I have only found one book devoted to the
> > subject
> > > > > and I
> > > > > > > > > regret
> > > > > > > > > > > > > buying
> > > > > > > > > > > > > > it .... 'MCS and System Trading' by Volker
> > > > Butzlaff.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > I have also test driven TradeSim and MSA.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Referencing their trading apps.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > TS arranges the trades, as a time series,
and
> > > > > randomly
> > > > > > > > > walks
> > > > > > > > > > > > > through
> > > > > > > > > > > > > > all permutations to simulate 'live
> > trading'.....
> > > > it
> > > > > is
> > > > > > > an
> > > > > > > > > MM
> > > > > > > > > > > test,
> > > > > > > > > > > > > of
> > > > > > > > > > > > > > some kind, because equity is allocated
prior
> > to
> > > > the
> > > > > > > walk
> > > > > > > > > > > through.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > AB's backtester, in default mode, does
this
> > once.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > I assume other methods could be used ...
as
> > per my
> > > > > > > > pervious
> > > > > > > > > > XYZ
> > > > > > > > > > > > > > example:
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > - abcXdefghi with simultaneous trades on
day
> > 4,
> > > > > > > > > > > > > > - we can only achieve a finite set of
> > > > permutations,
> > > > > > > > > > > > > > - the outcome of massive sampling will
tend to
> > > > the
> > > > > mean
> > > > > > > +-
> > > > > > > >
> > > > > > > > > > > variance,
> > > > > > > > > > > > > > - we can simulate the eq outcomes using
random
> > > > > sampling
> > > > > > > > of
> > > > > > > > > > > uniform
> > > > > > > > > > > > > > size, ave the result per random series and
> > then
> > > > freq
> > > > > > > dist
> > > > > > > > > the
> > > > > > > > > > > means
> > > > > > > > > > > > > > (Central Limit Theoreom predicts a pseudo
norm
> > > > > dist).
> > > > > > > > > > > > > > > 30 selections per series * ? series will
> > > > achieve
> > > > > an
> > > > > > > > > approx
> > > > > > > > > > of
> > > > > > > > > > > > > > possible eq outcomes (I'm not sure if
> > > > distrubtions
> > > > > obey
> > > > > > > > the
> > > > > > > > > > > laws of
> > > > > > > > > > > > > > sample error ... I don't think they do).
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > TradeSims real life simulation assumes
> > > > stationarity
> > > > > > > (the
> > > > > > > > > > balls
> > > > > > > > > > > in
> > > > > > > > > > > > > the
> > > > > > > > > > > > > > bin, and their values will remain constant
> > into
> > > > the
> > > > > > > > future).
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > It also assumes that they will be selected
> > from
> > > > the
> > > > > bin
> > > > > > > > in
> > > > > > > > > > the
> > > > > > > > > > > same
> > > > > > > > > > > > > > order, or frequency to be absolutely
correct
> > (the
> > > > > order
> > > > > > > > > > doesn't
> > > > > > > > > > > > > > change anything only the frequency)....
to be
> > > > > precise
> > > > > > > > about
> > > > > > > > > > it,
> > > > > > > > > > > > > their
> > > > > > > > > > > > > > model assumes that if you have picked the
> > worst
> > > > > > > > historical
> > > > > > > > > > loss
> > > > > > > > > > > out
> > > > > > > > > > > > > > of the bin 2/1000 trades that you will not
> > only
> > > > > > > > experience
> > > > > > > > > > the
> > > > > > > > > > > same
> > > > > > > > > > > > > %
> > > > > > > > > > > > > > as the worst loss in the future but that
it
> > will
> > > > > also
> > > > > > > > only
> > > > > > > > > > occur
> > > > > > > > > > > > > > 2/1000 times.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > MSA puts all of the balls in the bin and
> > selects
> > > > > them
> > > > > > > in
> > > > > > > > a
> > > > > > > > > > way
> > > > > > > > > > > that
> > > > > > > > > > > > > > allows new combinations (frequencies)
until
> > all
> > > > > possible
> > > > > > > > > > > > > frequencies
> > > > > > > > > > > > > > are exhausted i.e. they assume
stationarity
> > only
> > > > in
> > > > > > > > values
> > > > > > > > > > but
> > > > > > > > > > > not
> > > > > > > > > > > > > > frequency of dist (they assume dist is a
> > > > probability
> > > > > > > > > > statement
> > > > > > > > > > > and
> > > > > > > > > > > > > > not a constant or series of
constants).... to
> > be
> > > > > > > precise
> > > > > > > > > > about
> > > > > > > > > > > it
> > > > > > > > > > > > > > they assume that if it can happen it will.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > So, stationarity is the issue.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > So many people are confusing variance with
> > non-
> > > > > > > > > > stationarity ....
> > > > > > > > > > > > > they
> > > > > > > > > > > > > > are being fooled by randomness e.g.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > we know that the trial records of fair
coin
> > > > tosses
> > > > > are
> > > > > > > > > > > stationary
> > > > > > > > > > > > > AND
> > > > > > > > > > > > > > they have a surprising range of outcomes
> > > > > (variance) ...
> > > > > > > > > this
> > > > > > > > > > is
> > > > > > > > > > > > > very
> > > > > > > > > > > > > > easy to see if simulated and expressed as
> > equity
> > > > > > > outcomes.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Therefore, in trading, we can, at the
least
> > > > expect a
> > > > > > > > > > tremendous
> > > > > > > > > > > > > > amount of variance ... no less than what
can
> > be
> > > > > > > expected
> > > > > > > > > from
> > > > > > > > > > a
> > > > > > > > > > > > > coin
> > > > > > > > > > > > > > toss experiment ... this variance can be
> > estimated
> > > > > > > using
> > > > > > > > > > several
> > > > > > > > > > > > > > methods, simulation being one easy, push
the
> > > > > computer
> > > > > > > > > button
> > > > > > > > > > and
> > > > > > > > > > > > > look
> > > > > > > > > > > > > > at the graph method.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > So, the value of the simulation is in
training
> > > > the
> > > > > mind
> > > > > > > > to
> > > > > > > > > > > accept
> > > > > > > > > > > > > > variance and mentally prepare for the
worst
> > case
> > > > > losses.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > However, it doesn't matter how we design
our
> > > > > systems we
> > > > > > > > can
> > > > > > > > > > not
> > > > > > > > > > > do
> > > > > > > > > > > > > > anything about stopping non-stationarity.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > Our system will get wiped out in OOS if
it is
> > not
> > > > > > > robust
> > > > > > > > OR
> > > > > > > > > > if
> > > > > > > > > > > the
> > > > > > > > > > > > > > market changes.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > If our system is robust it will still get
> > wiped
> > > > out
> > > > > if
> > > > > > > > the
> > > > > > > > > > > market
> > > > > > > > > > > > > > changes.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > However, IMO, non-stationarity is not, or
need
> > > > not
> > > > > be,
> > > > > > > as
> > > > > > > > > > > pervasive
> > > > > > > > > > > > > > in trading as we think.
> > > > > > > > > > > > > >
> > > > > > > > > > > > > > As I have said in the past, and already in
> > this
> > > > > > > post ...
> > > > > > > > > many
> > > > > > > > > > > > > traders
> > > > > > > > > > > > > > are slayed by the innocuous looking Black
> > Swan,
> > > > > because
>
...

[Message clipped]  



__._,_.___


**** IMPORTANT PLEASE READ ****
This group is for the discussion between users only.
This is *NOT* technical support channel.

TO GET TECHNICAL SUPPORT send an e-mail directly to
SUPPORT {at} amibroker.com

TO SUBMIT SUGGESTIONS please use FEEDBACK CENTER at
http://www.amibroker.com/feedback/
(submissions sent via other channels won't be considered)

For NEW RELEASE ANNOUNCEMENTS and other news always check DEVLOG:
http://www.amibroker.com/devlog/





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

__,_._,___