Matstat Econometrics Matan - page 24
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
Many people simply forget that estimating a correlation does not mean having one at all.
Two identical processes can have a correlation of zero over the lifetime of the processes. And this should always be taken into account.
haha, genius post
but
100% agree
No.
There are sections with positive and negative correlations.
There is a stock-o and a stock-p, a stock and a futures, an index and a basket of its stocks, etc. But the fish aren't usually there anymore.
No.
There is no such thing.
No.
There is no such thing.
How's that?
One person starts pouring out a glass of water, at the same time another person in the other hemisphere also starts pouring out the same glass of water. They pour it out at the same rate. The correlation of the processes of pouring out the same glass of water at the same rate is 100%. But in fact there is no correlation between these processes.
One person starts pouring out a glass of water, at the same time another person in the other hemisphere also starts pouring out the same glass of water. They pour it out at the same rate. The correlation of the processes of pouring out the same glass of water at the same rate is 100%. But in fact there is no correlation between these processes.
Read it again - it's about financial markets. And only about them.
One person starts pouring out a glass of water, at the same time another person in the other hemisphere also starts pouring out the same glass of water. They pour it out at the same rate. The correlation of the processes of pouring out the same glass of water at the same rate is 100%. But in fact there is no correlation between these processes.
By the way, there is.
Both processes have a functional relationship - both processes are described by the same physical law. Shall I give you a link?
It is a rare case where the correlation of two assets is constant (and equal to zero, for example). Typically, market assets change their "modes of operation", periods of high correlation change to low correlation, etc.
Of course, everything is within reasonable limits. But the idea here, too, is that estimating correlation without analyzing the correlation of assets is of little use. In general, valuation is needed when there are many instruments, by valuation we select the ones that fit the characteristics, and then by analysis we weed out the ones we don't need.
And when there are few instruments, estimation is usually confirmation of analysis. And if there are discrepancies, it means that it is necessary to recheck the analysis of correlation of assets.
One person starts pouring out a glass of water, at the same time another person in the other hemisphere also starts pouring out the same glass of water. They pour it out at the same rate. The correlation of the processes of pouring out the same glass of water at the same rate is 100%. But in fact there is no correlation between these processes.
study the correlation of rare events ? a power worthy of a nobel prize ! Seriously, one prize was given for collisions in small samples (got it right from memory ?)
If those two people started pouring water every day, for say a year, and often hit the same moments and volumes, there would be a correlation between them. And perhaps even love :-)