Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# st: RE: correlation, panel data

 From Nick Cox <[email protected]> To "'[email protected]'" <[email protected]> Subject st: RE: correlation, panel data Date Wed, 13 Oct 2010 17:49:20 +0100

```You should read the Statalist policy on repeated posts.

Pestering the list is likely to be counter-productive.

One possibility without installing anything is to modify this recipe:

sysuse auto
levelsof rep78, local(levels)
gen corr = .
qui foreach l of local levels {
corr mpg weight if rep78 == `l'
replace corr = r(rho) if rep78 == `l'
}

Nick
[email protected]

Biljana Dlab

I have panel data (sorted by gvkey_n and financial years).

Now I am trying to compute correlation between variables r_d and cf - I would like to have this correlation in a separate column in spread-sheet and that the correlation coefficient is written for all firm-year observations

With other words this is what I would like to get:

gvkey_n 	year corr(between r_d&cf)
555		99	0.2
555		00	0.2
555		01	0.2
555		02	0.2
333		99	0.4
333		00	0.4
333		01	0.4

I tried like this:
.by gvkey_n: corr cf r_d  - but then I get matrix (for all companies, very long list in my black stata field)

-> gvkey_n = 63651
(obs=6)

|      r_d 	cf
-------------+------------------
r_d |   1.0000
cf	 |   0.0620   1.0000

How do I select the r_d & cf combination form the matrix put it in separate column in my spreadsheet for each firm?

If I try:
. by gvkey_n: egen d_corr = corr(cf r_d) unrecognized command:  _gcorr r(199);

Trying:
. ssc install egenmore
checking egenmore consistency and verifying not already installed...
(no action taken)
r(602);

Do you know the function how to get correlation in the column?

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```