Bookmark and Share

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


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

st: Composite reliabilty of latent variables


From   "Alvaro Filipe da Costa" <[email protected]>
To   <[email protected]>
Subject   st: Composite reliabilty of latent variables
Date   Mon, 7 Mar 2011 14:08:07 +0100

Dear all,

I am looking for a way to calculate the ?composite reliability? of a
measurement scale for a latent variable (Source: Werts, C. E./Linn, R.
L./Jöreskog, K. G. (1974)) 
My situation is the following: I am using survey data, in which a particular
variable (such as ?Work satisfaction?) is measured by a number of reflective
likert-scale indicators (e.g. ? I am satisfied with my job ?). Using a
factor analysis I have determined the scores for the latent variable. The
indicator loadings vary, so I assume that they do not enter the factor
calculation with equal weight.  

As far as I understood the Cronbach Alpha calculation provided by STATA
assumes that all indicators are equally weighted for estimating a latent
variable (Tau-Equivalence). The ?composite reliability? seems to offer a
reliability measurement without this assumption. Can anyone point me to
where I can find this functionality, or any alternative?

Thanks a lot for your consideration!
Filipe


*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index