This Thread is for a question about the Russell 100 and S&P...

C

cml2949

I hear that there is a 99% correlation between the Russell 100 and the S&P.. Anyone have any ideas? Please show links if you have any..

Thanks in advance

CML
 
Quote from jim c:

we are a MM firm...currently we have the RL to SP correlation at about 89%. jim
More...

Hey Jim how did you arrive on that percentage? Is there a way to confirm that to me?

Thanks
 
Quote from cml2949:

Thanks for the info.. How can you confirm that?

CML
More...

Setup a Excel spreadsheet. Enter the closing price of the SP in column 1 for each day of the year. In column 2 enter the closing price of the RL for each day of the year.

In column 3 at the bottom enter =correl(a1:a253,b1:b253)
(253 is the number of days in the year)
Multiply the number by 100 and you'll get 92.7 for 2005.

This can also be done on intraday data by selecting a timeframe (5min., 10min. etc.) and populating a database. Then write a program to compute the correlation.
 
Quote from acrary:

Setup a Excel spreadsheet. Enter the closing price of the SP in column 1 for each day of the year. In column 2 enter the closing price of the RL for each day of the year.

In column 3 at the bottom enter =correl(a1:a253,b1:b253)
(253 is the number of days in the year)
Multiply the number by 100 and you'll get 92.7 for 2005.

This can also be done on intraday data by selecting a timeframe (5min., 10min. etc.) and populating a database. Then write a program to compute the correlation.
More...

Thanks for the advice.. I tried it for FEB and got little over .997..

CML
 
Quote from acrary:

Setup a Excel spreadsheet. Enter the closing price of the SP in column 1 for each day of the year. In column 2 enter the closing price of the RL for each day of the year.

In column 3 at the bottom enter =correl(a1:a253,b1:b253)
(253 is the number of days in the year)
Multiply the number by 100 and you'll get 92.7 for 2005.

This can also be done on intraday data by selecting a timeframe (5min., 10min. etc.) and populating a database. Then write a program to compute the correlation.
More...


usually correlation is calculated on percentage changes rather than price itself.
 
You must log in or register to reply here.
Back
Top