Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: Re: correlations


From   Nick Cox <n.j.cox@durham.ac.uk>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Re: correlations
Date   Tue, 8 Nov 2011 20:50:51 +0000

What you ask for still sounds like a round-about way of getting what you want. 

You can just ensure that the -statsby- results include the sample size. Then you have enough information in the file to calculate inferential results, with some extra assumptions. 

Alternatively, -corrci- at 

SJ-10-4 pr0041_1  . . . . . . . . . . . . . . . . . Software update for corrci
        (help corrci, corrcii if installed) . . . . . . . . . . . .  N. J. Cox
        Q4/10   SJ 10(4):691
        update to fix corrci so that it always saves r-class results

SJ-8-3  pr0041  .  Speaking Stata: Corr. with confidence, Fisher's z revisited
        (help corrci, corrcii if installed) . . . . . . . . . . . .  N. J. Cox
        Q3/08   SJ 8(3):413--439
        reviews Fisher's z transformation and its inverse, the
        hyperbolic tangent, and reviews their use in inference
        with correlations

gives you confidence intervals, arguably more informative than just starring results as if they were hotels or movies, although still often problematic. 

As these look like data in time, a different comment is to underline that the assumptions underlying correlation significance calculations include mutual independence. 

Nick 
n.j.cox@durham.ac.uk 

Rodrigo Briceño

I am applying the following command over my
database to get a stata file with correlations (working on Stata
11.2):

statsby, by(isin2) saving(correld): corr liq sap if ano>=2008 &  dsap0810==1

where isin2 is an identification number, liq and sap are the variables
where correlation should be applied and ano and dsap0810 are some
filters I need to apply. My question to the list is if there is some
additional command that I can use properly in order to have the same
output (ids and correlations for the selected periods) but instead of
having a separate file (correld.dta) to get the output on my results
window. Why do I ask this? because I would like to get the results
with their corresponding significance levels on the form of asterisks
(***).


*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index