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 on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: stata correlated correlations Olkin Finn


From   Eric Booth <ebooth@ppri.tamu.edu>
To   "<statalist@hsphsun2.harvard.edu>" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: stata correlated correlations Olkin Finn
Date   Sat, 11 Dec 2010 20:08:04 +0000

<>

-findit olkin finn- returns nothing for me. So, unless someone else has create some code to do this, you probably need to write the code yourself.

Take a look at this paper:  http://www.public.asu.edu/~davidpm/ripl/olkintech.cml.pdf
The paper details an error in Olkin/Finn (1995) and the last page of the report provides the SAS code for running the Olkin/Finn measure and the authors' correction of that measure.  You could use the formulas in this paper or from the SAS code they provide to produce what you need.  The SAS code looks to be transportable to Stata without many changes.  

For instance,  they calculate the difference between the raw and partial correlation in SAS with this code:
 
      diffr=rxy-((rxy-rxm*rmy)/((sqrt(1-rmy*rmy))*(sqrt(1-rxm*rxm)))))

which can be run Stata if you add a -generate- command to the beginning.

- Eric
__
Eric A. Booth
Public Policy Research Institute
Texas A&M University
ebooth@ppri.tamu.edu
Office: +979.845.6754
Fax: +979.845.0249
http://ppri.tamu.edu


On Dec 10, 2010, at 10:36 PM, <fabio.zona@unibocconi.it>
 wrote:

> Dear all,
> 
> I need to perform the test by Olkin and Finn (1995). Do you know how I can do that in Stata?
> 
> The reference is:
> Olkin and Finn (1995), Correlation redux. Psychological Bulletin, 118, 155-164
> 
> Another relevant reference is:
> Graf R.G., Alf E.F., jr. (1999), Correlations Redux: Asymptotic confidence limits for partial and squared multiple correlations, Applied Psychological Measurement, 23(2), 11116-119
> 
> 
> This test is very important as it allows to deal with concerns for common method bias that often arise with a single respondent survey.
> 
> Thanks
> 
> 
> *
> *   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/



*
*   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