How do I calculate average pairwise correlation?

[johnkim]

Dear all,
Hi, I have a dataset, where P_(i,j,t) is the stock price of firm i in sector j at time t.
I am interested in,
1. calculating average pairwise correlation of stock prices between firms in the same sector;
2. calculating average pairwise correlation of stock prices between firms in two different sectors.
I feel like there must be an efficient way of doing this, but I'm not aware of it. I'd really appreciate your guidance. Thank you!

Best,
John

[Christos Makridis]

Why doesn't using "corr" work? A fast way of doing it is to use loops and making good use of locals. For example, here's one:

corr res_leis_hour dlgdp
local temp1: di %3.2f r(rho)

that saves the corr between the two variables to the temp1 local that you can call later and insert into a matrix, for example

[wbuchanan]

You may want to look at the mixed effects estimators if you need to decompose things into within and between industry effects/correlations. The icc command may also be useful for you.

[ben earnhart]

this is an odd use of the command, but alpha varlist, det std will give the average interitem correlation for a list of variables. Is that what you're after?