From theory to practice - page 11
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
:))) Doesn't it look like it?
you can check if you have 10 minutes of time
you can check if you have 10 minutes.
really a physicist?
I have several friends who are physicists. So they don't even understand each other. And in some cases even themselves).
:)))) Greetings Yuri, well, yes - there is that. However - yes, the shameful stories of people with some degree of technical education here on the forum do make you think and speak as little as possible.
:)))) Greetings Yuri, well, yes - there is that. However - yes, the shameful stories of people with some degree of technical education here on the forum do make one think and speak as little as possible.
Alexander, can you be more specific about WMA? Kill, I don't understand about the period.
What difference does it make! A wawa is a wawa, the delay is half a period, and these adaptive ones are a dime a dozen.
Speaking of Steudent. Yesterday I thought that if one puts MA on Wiener and calculates the distribution relative to MA, normality must break down and tails must appear. Less than in the market but they should appear. Of course I am not !00% sure, I will look at it one day.
I've already looked - the linear deviations of price from the MA have tails and they are, absolutely correctly, smaller than the increments.
Much more interesting to look at these linear deviations from the WMA. That's one I haven't looked at. And somewhere deep down (somewhere very deep :))) I think that these deviations "tend" to this t2-distribution. And the maximum similarity is achieved at a certain optimal sample size. That's what I'm saying - once born at the level of returns, t2-distribution can't just disappear - otherwise how else do we get the self-similarity property of the market?
Who cares! A mashka is a mashka, a half-period lag, and these adaptive ones are a dime a dozen.
By a quarter. For SMA.
I've already looked - the linear deviations of price from the MA have tails and they are, absolutely correctly, smaller than the increments.
Much more interesting to look at these linear deviations from the WMA. That's one I haven't looked at. And somewhere deep down (somewhere very deep :))) I think that these deviations "tend" to this t2-distribution. And the maximum similarity is achieved at a certain optimal sample size. That's what I'm saying - once born at the level of returns, t2-distribution can't just disappear - otherwise how else do we get the self-similarity property of the market?
By MA we meant smoothing in general, i.e. any LF filter. In theory, the tails for a proper WMA on Wiener should be longer than for a simple MA or EMA - the deviation will be smaller, and the tails will be relatively longer.
Well, we've just established ourselves that some of those tails are produced by the methodology itself. And Wiener itself is self-similar.
For a quarter. For the SMA.
For some reason I thought it was half. Fuck it.
once even wrote an article that any indicator based on smoothing ideas is irrelevant to a quote because the approximation error has a variable variance and can reach arbitrary values multiple of three sigmas. This is on the surface. People trading know it very well on their own depo.
Moreover.
If we take some smoothing, even the most abstruse one, and build a regression for it, the parameters of such a regression will not always be significant.
Therefore any idea of smoothing must be used very carefully in trading.