Bookmark and Share

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

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

Re: st: assessing model fit when using method(mlmv) vce(cluster clustervar)

From   John Antonakis <>
Subject   Re: st: assessing model fit when using method(mlmv) vce(cluster clustervar)
Date   Mon, 23 Jul 2012 14:58:25 +0200


At this time, Stata cannot do it, unfortunately, with -sem-. This is technically possible. Stata can do this with ivregress if the -robust- or -cluster- option is used. Likewise, so can -overid- do it. Mplus, a competing SEM software package does provide a robust chi-square test of fit so it is also possible with latent variables (Mplus even allows categorical and ordinal indicators, as well as a robust test of fit based on a WLS estimator). I hope that the Stata people are listening in and will plan this on the next -sem- upgrade (I have made this suggestion already to technical support).



Prof. John Antonakis
Faculty of Business and Economics
Department of Organizational Behavior
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny
Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305

Associate Editor
The Leadership Quarterly

On 23.07.2012 05:48, Stratford, Brandon J. wrote:
I am new to sem in stata. How does one assess model fit when using cluster-robust variance estimation? I am only provided with SRMR and CD when I ask for goodness-of-fit indices.

Brandon Stratford, LICSW
PhD Candidate
Bloomberg School of Public Health
Johns Hopkins University
*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index