Differences between LISREL and M+ out... PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Rene Algesheimer posted on Friday, February 08, 2008 - 6:10 am
Greetings,

I am new to M+ and I am thinking about to switch from LISREL. Therefore I tried to calculate a simple CFA with 2 factors and 3 indicators each (with estimated variances of factors, estimated cor amoing facotrs, estimated residual variances and no corelation among errors and ML estimation) in both packages and I received two completely different results, e.g. the RMSEA in LISREL is .000, in M+ .138. Therefore, I think that I made a mistake. I would greatly appreciate if someone can help me finding my mistake.

Here is the LISREl part:
mo ny=6 ne=2 ly=fu,fi te=fu,fi ps=fu,fi be=fu,fi
fr ly 1 1 ly 2 1 ly 5 2 ly 6 2
va 1 ly 3 1 ly 4 2
fr ps 1 1 ps 2 2 ps 2 1
fr te 1 1 te 2 2 te 3 3 te 4 4 te 5 5 te 6 6

Here is the M+ part:
model: y1 by x1 x2 x3;
y2 by x4 x5 x6;
Output: standardized; residual;

Many thanks in advance,
Rene
 Linda K. Muthen posted on Friday, February 08, 2008 - 6:27 am
You should check if you have the same number of observations, the same number of parameters, and the same sample statistics. If these are all the same, you should obtain the same parameter estimates and standard errors. Mplus and Lisrel differ in how the obtain some fit statistics. If you want further clarification, you should send the two full outputs to support@statmodel.com.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: