Dependency statistics in quotes (information theory, correlation and other feature selection methods) - page 62
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
That's the thing, they are not normal, but God forbid stationary, or not quite stationary, dependent or not quite dependent..... On top of all that, there are also errors in the estimated model parameters.
But that's the specifics that are not available when trading on paternals.
Doubtful. This is where econometrics fails completely.
The main approach is all sorts of regression models, assuming discontinuity and consistency of the model.
Doubtful. This is where econometrics fails completely.
The main approach is all sorts of regression models, which assume discontinuity and consistency of the model.
It's not clear.
I am interested in two things:
1. does econometrics treat the forecast as a price/time coordinate, or e.g. price/open date - what does level forecast mean? Does econometrics consider a forecast not a point/level but a trend change?
2. A particular forecast model or generally any forecast from an econometric perspective decreases at each successive step?
And more details for the layman, please ;)
1. Econometrics doesn't look at anything. Econometrics is a large set of tools for measuring economic data. A model is made and a forecast is calculated from it. A model for level means a forecast of level. A model for an increment means a forecast for an increment. A model for reversals means a forecast for reversals, etc.
2. There is no such thing as a predictive model. Just a model and any model can be used to calculate its values forward. I don't understand what a "forecast decreases" is. Forecast error grows. Econometrics has nothing to do with it. The thing is obvious. The further the target, the greater the spread.
OK, Nikolai, what don't you understand about the topicstarter's first post? What repulses you that you don't accept?
Well, I'm tired of answering questions that don't even have a question in them...
That's the point, it's understandable. What repulses me is the way, the methodology of applying TI. Ignoring the structure of price movement (which is paramount in information transmission) and background discretization. The market is fractal (i.e. scalable) and fractals are not described and studied head-on. Other approaches are needed.
Here is the link http://www.cognitivist.ru/er/kernel/prologi_11_scale_free_network.xml
It goes something like this.
And in a toonk - why is it unavailable in patterns?
Doubtful. This is where econometrics fails completely.
The main approach is all sorts of regression models, assuming discontinuity and model constancy.
Don't care about the structure of movement within an hour. It is a minimal atom, an indivisible part of the model.
Discretisation... OK, which one are you suggesting?
The market is fractal (i.e. scalable) and fractals are not described and studied head-on. Other approaches are needed. [...]
Here is the link http://www.cognitivist.ru/er/kernel/prologi_11_scale_free_network.xml
These are scale invariant networks. Our result shows that there is no scale invariance.
No fractality as a consequence either. This is an EWA myth that is not supported by anything.
1. Econometrics does not look at anything. Econometrics is a large set of tools for measuring economic data. A model is made and a forecast is calculated from it. A model for level means a forecast of level. A model for an increment means a forecast for an increment. A model for reversals means a forecast for reversals, etc.
2. There is no such thing as a predictive model. Just a model and any model can be used to calculate its values forward. I don't understand what a "forecast decreases" is. Forecast error grows. Econometrics has nothing to do with it. The thing is obvious. The further the target, the greater the variation.
"1. Econometrics is not looking at anything. Econometrics is a large set of tools for measuring economic data. A model is made and a forecast is calculated from it. A model for level means a forecast of level. A model for an increment means a forecast for an increment. A model for reversals means a forecast of reversals, etc."
Would it then be correct to say that econometrics is a calculator with templates? Econometrics does not postulate axioms and theorems and does not present hypotheses. And would the expression "from the perspective of econometrics" be meaningless, for example, as we say in relation to the same physics?
"2. There are no predictive models. Just a model and by any model you can calculate its values forward. I don't understand what "prediction decreases" means. Forecast error grows. Econometrics has nothing to do with it. The thing is obvious. The further the target, the greater the variation."
It means that the reliability of the prediction decreases. It gets smaller with each step. Is that right?
Accessible. If the pattern is in analytical form. But even for indicators I have never seen a P-square.