Econometrics: one step ahead forecast - page 83

New comment
 
anonymous:


Let p[i], i=1...n - vector that contains the initial time series (price values over some period).

1. Calculate price increments: r[i]=p[i+1]-p[i], i=1...(n-1)

2. Mix the vector of price increments and get: r2[i], i=1...(n-1)

3. Calculate the cumulative sum of the vector r2: p2[1]=0; p2[i]=p2[i-1]+r2[i-1], i=2..n

Test the model on the obtained data p2[].

Numerical example:

p={0.9379413 0.1411467 0.2540312 1.5440039 1.2363895} // some price series

r={-0.7967946 0.1128845 1.2899727 -0.3076144} // differentiate

r2={-0.7967946 -0.3076144 0.1128845 1.2899727} // shuffle

p2={0 -0.7967946 -1.1044090 -0.9915245 0.2984482} // integrate

Thanks for the specific answer. I'll have to think about it. So far in EViews I don't understand how to do the shuffling. There is a bootstrap checkbox, but I don't know how to use it. I have to think about it.
 
Mathemat:
ARIMA. The meaning of the parameter d is explained there. It is the order of differentiation.
And the official translation is given above
 
faa1947:
Thanks for the specific answer. I'll have to think about it. So far in EViews I don't understand how to do the shuffling. There is a bootstrap checkbox, but I don't know how to use it. I have to think about it.


If you have data in csv format, please send it here and I will do it. In R language the suggested conversion is done simply:

mix.ts <- function (ts) {
  cumsum(sample(diff(ts), length(ts) - 1))
}
 
anonymous:


If you have data in csv format - you can upload it here and I will do it. In R language the suggested conversion is done simply:

Attached is the data for which I posted the result in the thread. The model used:

EURUSD hp1(-1 to -2) hp1_d(-1 to -1) eq1_hp2(-1 to -3) eq1_hp2_d(-1 to -4)

hp1 = HP(1/dx) - Hedrock-Prescott smoothing for the inverse value of the dollar index - second column in the file.

eq1_hp2 = hp(EURUSD - ( hp1(-1 to -2) hp1_d(-1 to -1))

It's not that simple. I don't understand what we are using.

Files:
kotir11.zip  2 kb
 
faa1947:
And the official translation is given above
But it has to be understood. Since you have undertaken the thankless task of introducing others to econometrics, you will also have to explain terms like ARMA, ARIMA, ARCH, etc. that no one understands.
 
Mathemat:
But it has to be understood.

Without reading the relevant Marxist-Leninist literature, this kind of understanding between the peoples cannot be achieved
 
The official translation is inadequate, but unfortunately already accepted by the Russian-speaking community.
 
Mathemat:
The official translation is inadequate, but unfortunately already accepted by the Russian-speaking community.
Come on. ARIMA - autoregressive integrated moving average These authors are inadequate
 
Mathemat:
But it has to be understood. Since you have undertaken the thankless task of introducing others to econometrics, you will also have to explain terms like ARMA, ARIMA, ARCH, etc. that no one understands.
About 40 years ago Box and Jenkins wrote a book about ARMA, 300 pages long - you think too much of me that I can do that in a short form on the forum.
 

ARIMA - autoregressive integrated moving average Это авторы неадекватные

Well I was talking about ARCH. Someone is definitely inadequate.

Autoregressive conditional heteroskedasticity

Or

Autoregressive conditional heteroskedasticity

1...767778798081828384858687888990...139
New comment