From theory to practice - page 620
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Something has got me interested in this distribution as a model for returnees:
https://en.wikipedia.org/wiki/Skellam_distribution
It is extremely similar to the real incremental distribution and its values are, come to think of it, by the difference of two quantities with Poisson distribution.
If it is true, then we can argue that the price itself has a Poisson distribution with respect to the expectation in the sliding window. And Poisson distribution tends to normal with a large sample size...
Here, do what you want with me, but the theory of Gaussian, Wiener processes such as Ornstein-Uhlenbeck process with return to the mean has not been fully exhausted.
I suspect we must increase the time intervals between reading tick quotes (specifically - work in high order Erlang's flow) and in a sliding window at least twenty-four hours.
I run my TS with 60th-order Erlang's flow (read once a minute on the average) and window = 24 hours - it will be interesting to compare my quotes with OPEN/CLOSE M1...
Suppose there will be rare trades (God forbid, I'm ready to be patient), but graceful.
P.S. I also do not forget about autocorrelation - let's see if it is exponentially decreasing at longer times, as Ornstein and Uhlenbeck require.
Now here's the thing to say.
I look at incremental distributions and how they change their statistical moments depending on quotation reading intervals, and I realise that market prices do NOT have the property of self-similarity. This property is unique to processes with stable, infinitely divisible (e.g. normal) distributions of increments - such as Brownian motion. This is not the case in the market.
Obviously, Mandelbrot and his fellows, who have no knowledge of physics (and even worse - they have knowledge, but hide it carefully), intentionally deceived the desperate people, so that they would go to scalping on tick data and small timeframes, and fill their bottom pockets by losing their deposits.
So that's it!
Some immediate thoughts: as the TF increases, we get closer to the SB, which implies:
1) The principle of fractality breaks down
2) Signs of SB-growth are inherited
Also said.
P.S. Google S.V. Bulashev Statistics for the trader. Bulashev gives the notion of a generalised exponential distribution. p. 43
Also said.
I would clarify - not to the delta-correlated ACF SB, but to the Ornstein-Uhlenbeck process (SB with exponentially decreasing ACF) with a return to the mean. The Lord God Himself is coming to the sufferers, those who are going through a long road of disappointment, and giving such a process. But, it has yet to get there.... I'm still on my way....
:))))
I'd, after all, finish the 'ears'. I don't know how you got them - but I remember some great deals with them.
If it's a bad one, you need to analyse the reasons, and Koldun is right - you need a thorough debriefing.
But if the "average", without analyzing the reasons, there is a profit of at least 25% per month, albeit with losing trades - we should just bet on the real and not bother. IMHO.
I think that the magician has done the following:
1. BP - increments.
2. direct Fourier transform, we have a spectrum
3. initial (required) signal is a sinusoid, we apply a Winner-Kolmogorov filter to the spectrum
4. we leave the frequencies, according to the mimimum standard deviation from the original signal
5. The best sinusoid is plotted on the incremental graph
----
PS: 6. We make sure that there is no fish in it.
I assume that the sorcerer did the following:
1. BP - increments
2. Direct Fourier transform, we have a spectrum of frequencies and amplitudes.
3. Initial signal is a sinusoid, so we apply the Winner-Kolomogorov filter to the spectrum of increscence
4. we keep frequencies, according to mimimum standard deviation from the original signal
5. Plot the best sinusoid on the incremental graph
Didn't hold back, sorry. You have sine waves everywhere, not a single straight, curve, or twist. That means you are trading exclusively flat.
I assume that the sorcerer did the following:
1. BP - increments
2. Direct Fourier transform, we have a spectrum.
3. Initial (desired) signal is a sine wave, so we apply a Winner-Kolmogorov filter to the spectrum
4. we leave the frequencies, by mimimum standard deviation from the original signal
5. Plot the best sine wave on the incremental graph
----
PS: 6. We make sure that there is no fish in it.
Point 1 - no question.
The rest is a waste, since there are no fish!
I have seen a couple of BP graphs he uses. It's almost impossible to visually see how he got them.
I couldn't help it, sorry. You have sine waves all over the place, not a single straight, curved or twisted one. That means you're trading exclusively flat.
No
the sorcerer was showing a sine wave in increments and K_2 is scratching his head about how to do it, that's the only reason
I'm just trying to read this thread...
that's why it helps with the boredom
Point 1 - no questions asked.
The rest of it, screw it, since there are no fish!
I've seen a couple of BP charts he uses. It's almost impossible to see how he got them visually.
I've already written how.
and that there's no profit in it, either.
All the Kolmogorov's articles (I did read something today) rely on the fact that the initial signal is known. You're going for nothing, relying on this kind of literature....
The initial signal in our case is not our signal, but the quote's target. We correct the movement towards this target to avoid formation of a straight line + to get more counter-trenders. This target will never be calculated, no matter how hard you try.