From theory to practice - page 67

 
Alexander_K2:

The final versionof the forex keys. Here it is:

1.Tick data receptionmethod-ANY

2. volume of tick data sampling -ANY

Calculated from Chebyshev inequality, so that this volume contains at least 99% of values of incremental distribution

3. Sampling measure of central tendency -NEEDED

In general it is a simple arithmeticmoving average SMA.

4. current variance -NEEDED

Calculated for the current sample size when each new tick is received

5. Historical average variance -NEEDED

Calculated based on historical historical data for the current sample size.

6. Current asymmetry coefficient-NONE

Calculated for the current sample size as anonparametric skew at each new tick

7. Historical average skewness factor -NONE

Calculated as anonparametric sk ew module based on archived historical data for the current sample size.

Bullshit and ignorance!

The market is NOT stationary and all values found will change over time.


How can we protect the forum from individuals who are unwilling on principle to read the special literature, who on principle do not provide evidence for their inferences?

 
СанСаныч Фоменко:

Bullshit and ignorance!

The market is NOT stationary and all found values will change over time.


How to protect the forum from people who on principle do not want to read special literature, on principle do not provide evidence for their conclusions?

Oh, come on. This is a forum block with general discussions, not a special section. Then almost the whole forum will have to be shut down. And when you consider that the special literature is not a guarantee of profit, it's too much. You would think that the few who are successful prove their conclusions. Let's have a botanical selection when registering on the forum.
A lot of nerds have been here, competing in the sophistication of theories, I doubt that all of them have left with the money.

 
СанСаныч Фоменко:

The market is NOT stationary and all found values will change over time.

Stationary or non-stationary is all relative.

If the process is stationary in the interval of, say, 5 m, and I need this interval, the process is stationary for me. Moreover, I may not be at all concerned about properties of the process beyond these 5 m, and even the existence of the process in general. The same can be repeated by substituting -non-stationary.

 
Yuriy Asaulenko:

Stationary or non-stationary is all relative.

If the process is stationary in the interval of, say, 5 m, and I need this interval, then for me the process is stationary. Moreover, I may not be at all concerned about properties of the process beyond these 5 m, and even the existence of the process in general. The same can be repeated by substituting -non-stationary.

I completely agree with you when studying history.

But the problem is that NOT stationarity will be "beyond" where you will make trading decisions. This is the point of NOT stationarity in that you will be making decisions in areas that have NOTHING to do with the beautiful, stationary history you have studied. And the worst part is that the variance is bound to be multiples (or maybe orders of magnitude) greater than what you get on the stationary plot

 
Have I calculated the RMS correctly?

Here is the formula:


Here is the result in excel:
Files:
wmy4m2.zip  990 kb
 
Максим Дмитриев:
Am I calculating the RMS correctly?

Here's the formula:


Here's the result in excel:

Take n equal to, for example, 100. Count the sko, then move the window by 1 and count again. and so on 100 times. You will be able to plot the sko. For some reason it seems to me that the sko will be variable. And if it is, then everything written on the 69 pages is just nonsense.

 
СанСаныч Фоменко:

Take n equal to, for example, 100. Count the sko, then move the window by 1 and count again. and so on 100 times. You will be able to plot the sko. For some reason it seems to me that the sko will be variable. And if it is, then everything written on the 69 pages is just nonsense.


Of course it will be variable, that's what Bolinger is built on.

Bollinger Bunds is the SCO deferred from the MA, subtract the BB lines from its swing and you get the SCO.

There's even in the BB settings how much RMS to defer from the waving.

 
СанСаныч Фоменко:

Take n equal to, for example, 100. Count the sko, then move the window by 1 and count again. and so on 100 times. You will be able to plot the sko. For some reason it seems to me that the sko will be variable. And if it is, then everything written on the 69 pages is just bollocks.


The question is "how variable". How much will it vary from week to week (month to month).

 

What is the advantage of a standard deviation over a simple average deviation?

 

wanted to calculate the standard deviation and found out that this is the same as cattle )

Reason: