Correct calculation of currency indices. - page 14

 
faa1947:

This is the formula by which the index is calculated

I know that. I don't think it's transparent (correct) in the very way it's found by this scheme. But that's personal and I won't argue about it.
 
Neutron:
That I know. I don't think it's transparent (correct) the very way of finding it in this scheme. But this is personal and I won't argue about it.
I don't think the choice of formula is serious without the choice of selection criterion. as such criterion I would use something from the criteria related to non-stationarity of the market. I mean, people exercise in Box-Cox. If we are going to build a TS based on an index, then maybe the calculation of the index will affect the stability of the TS
 

All of this needs to be checked.

As of today, I can state that there is no meaningful cross-correlation between currency indices and currency instruments and it does not depend on the way the index is constructed.

 
Neutron:

All of this needs to be checked.

As of today, I can state that there is no meaningful cross-correlation between currency indices and currency instruments and it does not depend on the way the index is constructed.

My thread shows that using an index improved the results of the model by a factor of one and a half. DX was used for the days. Gaps were filled by linear interpolation. About the method of calculation - don't know
 
faa1947:

kills me - I don't understand what's here and where it's coming from.

It is the formula by which the index is calculated

This formula shows :

The calculation of the dollar index (USDX) on a basket of six currencies is not accidental - it matches the data used by the US Federal Reserve in calculating the trade-weighted dollar index on the currencies of those countries that form the main US foreign trade turnover. Most of US international trade is with the Eurozone (57.6%), followed by Japan (13.6%), the UK (11.9%), Canada (9.1%), Sweden (4.2%) and Switzerland (3.6%).

And it was derived a hell of a long time ago. Since then, the US foreign trade ratio has changed considerably (e.g. China stormed in like a typhoon). Therefore the formula is, at the moment, worthless.

 
BoraBo:

And it was taken out a heck of a long time ago. Since then, the US trade balance has changed considerably (e.g. China stormed in like a typhoon). The formula is therefore, at the moment, worthless.

Can't you give the typhoon value - % in US trade turnover. % of US trade turnover by 6 countries in total US trade turnover. The words "about nothing" need to be proven, it's just about nothing here.
 
faa1947:
Can we give a typhoon value - % in US trade turnover. % of US trade turnover for 6 countries in total US trade turnover.

The calculation of the dollar index (USDX) by a basket of six currencies is not accidental - it matches the data used by the US Federal Reserve in calculating the trade-weighted dollar index by the currencies of those countries which make up the main US foreign trade turnover.

Because I'm far from the Fed, I can't give reliable data on US trade turnover, but you can look it up online if you need those figures that badly.

faa1947:
The words "about nothing" need to be proven, it just doesn't roll here.

You don't have to prove "nothing" because there is no subject to prove, you have to prove the validity of the index in some context.

For example, prove that there is a significant cross-correlation between indexes and currency symbols, and it strongly depends on how the index is constructed.

 
BoraBo:

Because I am far from the Fed, I cannot give reliable data on US trade turnover, but you can search the internet if you need these figures so badly.

You don't have to prove "nothing" because there is no subject to prove, you have to prove the validity of the index in some context.

For instance, prove that there is a significant cross-correlation between indexes and currency p airs, and it strongly depends on how the index is constructed.

No need to jump off topic. "About nothing" is your statement. Prove it as you see fit, If you don't want to, you can't - no need to flub in relation to concepts that apply all over the world.
 
faa1947:
There is no need to jump off topic. "About nothing" is your statement. Prove it as you see fit, If you don't want to, you can't - no need to flub in relation to concepts that apply all over the world.

Understand, among the "gl obally applied " concepts there are not only useless, but even harmful.
 
PapaYozh:

Understand, there are plenty of "globally applicable " concepts that are not only useless, but even harmful.
Let's not generalise. We are talking about the dollar index. Let's have your opinion and justification. By the way, right on topic.
Reason: