Re: st: Common Factor Analysis

[Stas Kolenikov <skolenik@gmail.com>]

Given that there is no real model in EFA, and you can turn around your
analysis with thousands of options like # of  factors, rotation, etc.,
there is no real point in computing the standard errors or confidence
intervals. For any fixed procedure, you can do that; but for EFA as a
method, and the way it is used in practice, the differences between
the factor models produced with these different options will far
exceed the standard errors, so the latter do not serve the purpose of
quantifying the uncertainty about your estimates.

-- 
-- Stas Kolenikov  ::  http://stas.kolenikov.name
-- Senior Survey Statistician, Abt SRBI  ::  work email kolenikovs at
srbi dot com
-- Opinions stated in this email are mine only, and do not reflect the
position of my employer


On Thu, Aug 16, 2012 at 4:49 PM, Afif Naeem <afeef745@hotmail.com> wrote:
> Hello,
>
> I am using Common Factor Analysis as part of my research, and it is being used in an exploratory manner rather than confirmatory manner. I know there is a way (and I dont know it yet) to report t-value for each of the factor loadings associated with the variables used in confirmatory Factor Analysis. I want to know if there is a way to get the t-value for factor loadings for the exploratory factor analysis (using command -factor-) as well?
>
> Thanks
> Afif
>
> *
> *   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/