Re: st: Differences between LISREL and SEM in Stata 12 that might cause the same model to give different results??

[Richard Williams <richardwilliams.ndu@gmail.com>]

At 11:13 AM 10/31/2011, Jonathan Richards wrote:
> Hey everybody-
>
> I have been trying to replicate other researchers' factor analysis
> measurement model (estimating the relationship between three observed
> variables and one latent factor). They ran the model using LISREL. I 
> have tried running the same model, using the same data, using the 
> structural equation modeling feature of Stata 12.
> But I get different results.

Different in what way? The coefficients are different, the standard 
errors are different, or what?

At a minimum, I would check to make sure the d.f. for the two are the 
same, and that any fixed values are fixed the same way in both 
approaches. There  only needs to be one difference in model 
specification to screw up your comparisons.

Make sure the latent var is getting normalized the same way with both 
approaches. If you get the same fit with both approaches, I would 
guess that you have different parameterizations of the model.

I've had pretty good luck replicating LISREL models in Stata. I 
sometimes have trouble with start values in SEM. If you want to 
maximize your replication chances, you can try initing as many SEM 
values as possible to what you got with LISREL.

I haven't done anything like vce(cluster clustid2) with SEM -- does 
LISREL even have a comparable option? What happens if you don't use 
it with either program?

-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW:    http://www.nd.edu/~rwilliam

*
*   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/