Econometrics: one step ahead forecast - page 70

New comment
 
Mathemat:

Continue to accompany the muv until the price is below the muv again. How does this follow-up work? In this case, we close the small position you opened on the left vertical line, and open a new microposition on a new bar. That is, our muv is relevant again, i.e. we have exactly the muv on the current bar. This is the "accompaniment" of the muv. And now we do this until the price is again below the muv.

All of this is great, of course, but you don't consider that the microposition (aka 1/13 muv) will be closed not at the price of the old 13 bars, but at the price of the current one, bar zero. Accordingly, on the next bar you just can not synchronize the position with the value of the muv, but the muv can do it: it simply removes the oldest bar from the calculation and takes the newest one. The only thing that can be done in this situation is to increase the averaging period further. But the problem is that as the averaging period increases, the price will move further away from the muvin, and it will take longer and longer for the price to return to its average value.
 
DhP:

I tend to believe that by teaching on the flow of price data, this is not achievable/receivable at all.

My attitude to thisis here .

Mistaken for someone else, mistaken for someone else
 

Moove accumulation in my example is the process of consistently selling the price over 13 bars. This is

sell( Clo[12] + Clo[12] + ... + Clo[ 0 ] ) == sell( 13 * MA( 0; 13 ) )

We can't do it instantly, we have to do it gradually over 13 steps.

 
Mathemat:

Moove accumulation in my example is the process of consistently selling the price over 13 bars. This is

sell( Clo[12] + Clo[12] + ... + Clo[ 0 ] ) == sell( 13 * MA( 0; 13 ) )

We can't do it instantly, we have to do it gradually over 13 steps.

Thank you, got it.
 
C-4:
All of this is great, of course, but you don't keep in mind that the close micropositions (aka 1/13 muv) will not be at the price of the old 13 bars, but at the price of the current, bar zero. Accordingly, on the next bar you just can not synchronize the position with the value of the muv, but the muv can do it: it simply removes the oldest bar from the calculation and takes the newest one. The only thing that can be done in this situation is to increase the averaging period further. But the problem is that as the averaging period increases, the price will move further away from the muving, and it will take more and more time for the price to return to its average value.

Take and calculate for yourself what equity will become on the 13th bar after you start buying. There is no netting, we trade in the DC!

I really sell the muv and really take care that the open short positions in total correspond to the sold muv (well, of course, with a factor of 13), making "accompaniment".

This is the next idea about increasing the period - a very useful one, by the way. But for now we need to understand the basic one.

 
You can't trade in clowns, but you can trade in oupans.
 
faa1947:
I mistook it for someone else, I mistook it for someone else.


Such versatility of a branch - a novel!

My five cents (San Sanych, forgive me if you can) .

Guys, the price space is one-dimensional. And if anyone has thoughts about participation of time in this mess, then let's remember about quantization in form of bars (candlesticks).

What does R^2 have to do with it then?

 
tara:

What does R^2 have to do with it?

Yes it has to do with NS. Tried to fill in the blank, but failed.
 
faa1947:
Yes it is in relation to NS. Tried to fill in the blank, but failed.


San Sanych, - excuse me, but the regression analysis...

It turns out - not R^2, but just h-something!?

 
tara:


San Sanych, - excuse me, but the regression analysis...

It turns out - not R^2, but just h something!?

I haven't seen any publications on NS with R^2. That's what I mean. What does regression analysis have to do with it?
1...636465666768697071727374757677...139
New comment