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: factor analysis - calculating Crohnbach's alpha


From   Kerry MacQuarrie <Kerry.MacQuarrie@icfi.com>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   RE: st: factor analysis - calculating Crohnbach's alpha
Date   Tue, 9 Oct 2012 20:30:12 +0000

Yes, you're right, Nick. A line after the rotate line reading,  predict factor1 factor2 factor3 (or however many factors shake out), would give me the scoring coefficients (regression coefficients to estimate individual scores).  But is that necessary for calculating the factor's alpha? I'm not seeing where alpha syntax refers to anything produced by the predict command.  Or is there a more appropriate syntax to use in place of the alpha command?

All guidance welcome.

Thanks,
Kerry

PS. Thanks too, Nick, for correcting my spelling of Cronbach's!  I guess I got a little H happy.

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Nick Cox
Sent: Tuesday, October 09, 2012 4:17 PM
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: factor analysis - calculating Crohnbach's alpha

You need a -predict- step too.

P.S. Cronbach

On Tue, Oct 9, 2012 at 9:12 PM, Kerry MacQuarrie <Kerry.MacQuarrie@icfi.com> wrote:
> The last time I conducted exploratory factor analysis, I was using SPSS because that is the software my overseas partners had.  Now I'm trying to figure out how to do a similar analysis in Stata.
>
> I will be using principal components factor extraction methods and 
> promax rotation.  I've quickly figured out the syntax for these two 
> steps.  However, I next want to assess each factor for internal 
> reliability (interitem correlation) using Crohnbach's alpha.  This is 
> where I am uncertain.  It appears that I can do the following (see 
> line 3 of code)
>
> Factor varlist, pcf
> Rotate, oblique promax(#)
> Alpha varlist, generate newvar
>
> Where varlist is a manually inserted list of each item that loaded onto the factor and newvar is the factor label; and where this line is repeated for each of the factors that I want to retain.
>
> Is there an easier way to do this?  A way to make the last step automatic for each factor extracted? It seems to me that SPSS automatically generated a table with each factor and its items' factor loadings and the Crohnbach's alpha for each factor.  I'd hate to think that SPSS is actually superior to Stata (gasp!) in this regard. Surely, I'm mistaken here.

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


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