From theory to practice - page 28

New comment
 
Alexander_K2:  In due course, we will continue the theoretical debate with the results in hand. OK?
Well, I'm ready now.)
 

I wonder, philosophically, why the future should depend on the past. Although the future is a continuous transition from the present, as I understand it is also a non-marking process.

So what are the chances that in the future a brick will not fall on your head (even while working on a construction site), if it has not happened before and up to the current second in the present and we have taken this history into account in our formulas.

Or what is the probability that Vasya Pupkin, driving his car for a long time along the same route, will not change it in the future and every time this route will not be repeated.

It's just a thought, if anything!

 

I hope everyone understands that one should not look at the current variance, or the historical average individually, but at the aggregate???

That's it. I'm out of here.

 
Alexander_K2:

I hope everyone understands that one should not look at the current variance, or the historical average individually, but at the aggregate???

That's it. I'm off.


The question is another one! Who moves the market. After all, he may not look at the variance and he does not care about the signals produced by ingenious formulas.

There is no 100% guarantee that the price at this moment will go where the mathematics and physics show.

 
Евгений:


The question is different! Who moves the market. After all, he may not even look at the variance and he does not care what kind of signals the clever formulas give.

There is no 100% guarantee that the price at this moment will go where the mathematics and physics show.

You're absolutely right.

The market is moved solely by speculators and only they. They are the ones who basically buy/sell at Buy and Sell and a price movement occurs. And this is where the maths and physics comes in, as the speculator is not one, there are many, and their behaviour can be described. Statistics and distributions appear.

And only insurance policy gives a 100% guarantee.

In Forex it is not so, but Forex is not the market either.

 
Alexander_K2:

I hope everyone understands that one should not look at the current variance, or the historical average individually, but at the aggregate???

That's it. I'm out of here.

Well, if you take Bollinger, his channel is the "current variance", and when you set the condition "let the price go beyond six sigmas", it is a constant, similar to your "historical average", you didn't get it from the ceiling, but from history. In other words, the "aggregate" has existed for a long time. I'm just trying to clarify the wording, if anything).

 
bas:

Well, if you take Bollinger, then his channel is the "current variance", and when you set the condition "let the price go beyond six sigmas", it is a constant, similar to your "historical average", it is not taken from the ceiling, but from history. In other words, the "aggregate" has existed for a long time. I'm just trying to clarify the wording, if anything)

Their love of the Good stirred their hearts. And Herzen was asleep, unaware of evil... 
But the Decembrists woke Herzen up. 
He did not sleep enough. That's where it all started. 

Ah, the Decembrists!... Don't wake Herzen!... 
You can't wake anyone in Russia. (с)
 
Евгений:

I wonder, philosophically, why the future should depend on the past. Although the future is a continuous transition from the present, as I understand it is also a non-marking process.

...

Because the present gives the future a narrow corridor of possibilities. And into the present we come from the past.

Once the present was also the future, and the past (at that time the present) also left its future a narrow corridor of possibilities.

 
Евгений:

I wonder, purely philosophically, why the future should depend on the past?

Because cause often causes effect. The market is driven by people (traders). And there are similarities in their behaviour, which makes the market sometimes predictable. For example, here is a cause-effect relationship: if you go to a bazaar square and fire a gun upwards, you can predict that everyone will start scattering in a coordinated manner. Although under normal conditions, the movement of people in a market square is more like a Brownian movement. The analogy in the stock market is a gap.
 
bas:

Well, if you take Bollinger, then his channel is the "current variance", and when you set the condition "let the price go beyond six sigmas", it is a constant, similar to your "historical average", it is not taken from the ceiling, but from history. In other words, the "aggregate" has existed for a long time. I'm just trying to clarify the wording, if anything)

A-ya-ya-ya-ya! Well, how could that be, eh? :))))

I thought we all understood... (((( Who am I going to fight in the tournament? ))))

One more time:

1. You take a certain sample size.

2. Calculate the RMS (but I, for example, consider a weighted RMS) - this is the current variance.

3. For a given sample volume, you generate 1,000,000 such samples from an archive set of tick data.

4. You calculate the average historical variance.

5. At the current calculation step, calculate the sum of these variances.

6. Multiply by the sigma of the Chebyshev inequality.

...

The same for Nonparametric Skew - calculate the historical one, compare it to the current one.

Supplement it with your own cunning intricacies.

That's it.

In return I ask:

Someone - tell me how the Nonparametric kurtosis coefficient is calculated!!!!!

1...212223242526272829303132333435...1981
New comment