Econometrics: one step ahead forecast - page 115
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
ok...then let's not torture...the HP trend stands out...using a simple example, look at the step by step (bar by bar)... The trend that you take should not redraw! (the first bars on the right) otherwise all measurements are meaningless and wrong ...
I don't recognise the sacred cow on overdrawing indicators. The model takes the maximum of the last 4 bars. What difference does it make what happens when you shift 1 step forward with those HP values? The last 4 bars again and so on.
Moreover, when shifting under the criterion of "correctness" I determine the number of bars from the HP, on the basis of which I calculate the forecast. You may see it in the last columns of the table. Values in parentheses are number of HH bars. It varies.
Here we are looking at the nature of the problems, not the year of birth.
It's just that you claim to have been investing since you were a baby ("all your life"), but given your advanced retirement age, it becomes problematic to imagine this type of activity in your Soviet days. Hence the question.
Look, you're stubborn to the point of self-loathing.... one more time:
Choose as your series model, the incremental model: B(n)=B(n-1)+epsilon(n) (everything developed, developed for it) rather than B(n)=trend1()+trend2()+...trendp()+e. You have no idea about the trend patterns that sit in it and can never correctly identify them, especially as they change from time to time. Price is a multifractal, a very complex process
for your model to be applicable, you need to get (otherwise the model is easier to throw away)
This is the minimum necessary (but not sufficient) With price this kind of thing doesn't work, try going to a transformation.
Did it for increments - much worse. In increments the trend is irrevocably lost. What you suggest is good for volatility forecasting. For me the presence of a trend is a guarantee of predictability of the model.
Once again, you are generating a series that has nothing to do with reality .
For your model to be applicable, you need to get (otherwise the model is easier to throw away):
My model has the property of reversibility: add the right hand side and you get a quotient. The incremental model does not have this property: you need the first value.
My model is 100% consistent with kotir.
It's just that you claim to have been investing since you were a baby ("all your life"), but given your advanced retirement age, it becomes problematic to imagine this type of activity in your Soviet days. Hence the question.
Well, why, in Soviet times they built much more than now, there is no need to equate. And planning and forecasting is the essence of socialism, not capitalism. Mat models on forecasting from books of early 80's in EViews are not implemented until now, people are discovering America in the form of dissertations. Not to mention the application of computers. Now it's primitive, implemented by small teams of people. Microsoft has 32k employees and I worked in an organisation with 10k employees - it was a medium-sized organisation.
Therefore, it is impossible to teach anyone what I knew how to do - the infrastructure for such training has been lost.
Made for increments - much worse. In increments the trend is lost irrevocably. What you suggest is good for volatility prediction. For me the presence of a trend is a guarantee of predictability of the model.
Once again, you are generating a series that has nothing to do with reality .
For your model to be applicable, you need to get (otherwise the model is easier to throw away):
My model has the property of reversibility: add the right hand side and you get a quotient. The incremental model has no such property: you need the first value.
My model is 100% consistent with kotir.
(1) I have shown you by the example of random walk that your claims are illusory
(2) this "My model is 100% consistent with kotir." is just a stupid statement, literally.
Well why, there was much more construction in Soviet times than now, you don't have to equate. And planning and forecasting is the essence of socialism, not capitalism. Mat models on forecasting from early 80's books in EViews are not implemented until now, people are discovering America in the form of dissertations. Not to mention the application of computers. Now it's primitive, implemented by small teams of people. Microsoft has 32k employees and I worked in an organisation with 10k employees - it was a medium-sized organisation.
Therefore, it is impossible to teach anyone what I knew how to do - the infrastructure for such training has been lost.
why did the alliance fall apart then? :o( Don't tell me it's just politics ...
(1) I have shown you by the example of random wandering that your claims are illusory
I know this without you. Only trending markets are predictable.
(2) this "My model is 100% consistent with the quotient." is just a silly statement, literally
Be more specific and without emotion. I have equality. level is obtained by adding in the right hand side, what is lost?
Why has the union fallen apart then? :o( Don't tell me it's just politics...
No politics, freedom of speech and democracy. In Yeltsin's book: I'm looking at a chair and it says "Upravlenie delami CPSU Central Committee" and I wonder when it will be mine. Ownership of that chair is what made it all happen.
No politics, no freedom of speech and no democracy. In Yeltsin's book: I look at the chair and it says "Management of the CPSU Central Committee" and I wonder when it will be mine. For the sake of ownership of this chair, everything happened.
So it was because Yeltsin wanted to pocket his own chair that the Soviet Union had to collapse?
Is this news to you? The helpers are there to grab a bigger chunk and on and on they go. Everything else is a cover-up operation to fool the idiots.
And yet you can elaborate. And without the florid context.
And yet, could you be more specific? And without the florid context.