Econometrics: one step ahead forecast - page 121
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
I won't be changing the recording format. That's for sure. The work of external experts is tied to this block. CSV is mainly needed for visualisation. I didn't need it.
I don't see the point of making an additional block of records in CSV. You're the only one who needs it now. It would take too much time to redesign the interface. Unprofitable.
Make your own reader. I'll send you the format.
You don't need a file to do this, but a black box function.
My job is to suggest it. If you read this thread at your leisure from the beginning, you'll see how much I could add to your system.
Most importantly, I have no problem with the prediction.
Make up your mind.
The RMS is fine if it is at least nearly constant. But if there is heteroscedasticity, it is definitely not. And heteroscedasticity can be different.
The idea was to take the window size proportional to the number of bars in ACF to zero correlation - this is the current memory length of the market.
RMS is almost a constant only for almost stationary series...
About the role of ACF, as an indicator of memory length information - it is of little use: compare ACF of different timeframes of the same market, oddly enough, but their values of lag correlation coefficients will be amazingly close ... Same proves using spectrum decomposition by Shunko - in any case they use wavelet transform and work with each of frequencies, after that they just either add or transform back for forecasting - each of filters works on lower frequency in any case, relative to forecasted value, that doesn't screw up forecast only on forward bar...
Most importantly, I have no problem with the forecast.
:) a very bold assurance, I would say illusory. But in the context of your correspondence with a colleague, here, you can read it if you're interested (it's been a while ...)
https://www.mql5.com/ru/forum/119541/page5
My biggest post on p. It works if you really know how to predict :)
:) a very bold assurance, I would say illusory. But in the context of your correspondence with your colleague, here, you can read it if you're interested (it's been a while ...)
https://www.mql5.com/ru/forum/119541/page5
My biggest post on p. It works if you really know how to predict :)
Read it. One question: why are you hissing on this thread and not making a substantive point?
About the forecast. Zhunko has this problem and I have a button. There is no problem pressing a button and getting a figure. The problem is trust in that figure. Zhunko doesn't get to that point - any figure is the absolute truth.
dasmen:
About the role of ACF as an indicator of the memory length of information - it has little use for it: compare ACF of different timeframes of the same market
Here's the result.
Taking from the beginning of the sample
Take starting from 100 bar
Take the trend change
Take the sideways
All different.
We take D1
Not like H4 at all
I read it. One question: why are you hissing in this thread and not speaking out?
About the forecast. Zhunko has a problem, I have a button. There is no problem pushing the button and getting a figure. The problem is trust in this figure. Zhunko didn't get to that point - for him, any figure is the absolute truth.
What do you mean "hissing", in fact I have already called you a woodpecker. Then I am not hissing but hissing since we classified the imitations of "natural" sounds.
I've said it, repeatedly, and I won't say it again. Keep banging the barrel. Your sounds of hitting that wretched trunk drown out all the voices around you. I won't waste any more time on your illusory "trends", that's enough.
Ahhhhhhhh I see, by "I have no problem" you mean you have envil software :)))) Well you go ahead colleague, in the words of the great Yoda, - you are cool though :)
What do you mean, "hissing", but I've already called you a woodpecker. Then it's not hissing, it's hissing now that we've moved on to classifying imitations of "natural" sounds.
I've said it, repeatedly, and I won't say it again. Keep banging the barrel. Your sounds of hitting that miserable trunk drown out all the voices around you. I won't waste any more time on your illusory "trends", that's enough.
Ahhhhhhhh, I see, by "I have no problems" you mean you have envil software :)))) Well, you are a fellow, in the words of the great Yoda, - you are a tough one, though :)
Once again you've hit the price and walked away, maybe you've got nothing to say?