Measurement Invariance testing PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Linda Bode posted on Friday, July 30, 2010 - 4:20 am
Hi!
For my Master thesis I have to test my data for measurememt invariance since I am comparing four countries with about 50 respondents each. Unfortunately, I never learned another program than SPSS and therefore I am trying to figure out how MPLUS works by myself. I read the User guide and the handouts, but I am still not sure how to do it. I wanted to start with a simple CFA for each country, but the program shows me the following Error warning:

One or more variables have a variance of zero. check your data and format statement.

I dont have any missing values in my data set, I checked it twice with SPSS.

This is my syntax in short (I have five more factors):

TITLE: CFA;
DATA: FILE IS "... CFA.dat";
VARIABLE: NAMES ARE a1 a2 a3 b1 b2 b3 c1 c2 c3 d1 d2 d3 e1 e2 e3 f1 f2 f3
g1 g2 h1 h2 h3;

ANALYSIS: ESTIMATOR IS ML;

MODEL: A BY a1 a2 a3;
B BY b1 b2 b3;
C BY c1 c2 c3;
D BY d1 d2 d3;
E BY e1 e2 e3;
F BY f1 f2 f3;
G BY g1 g2;
H BY h1 h2 h3;

OUTPUT: standardized;

I am not sure if i did it correct, I tried to work with examples i found on the internet.

I hope someone can help me.
Thanx
 Linda K. Muthen posted on Friday, July 30, 2010 - 6:45 am
It sounds like you are setting up the reading of your data incorrectly. Please send the input, data, output, and your license number to support@statmodel.com.
 Linda Bode posted on Friday, July 30, 2010 - 11:54 am
I am so sorry, I found the mistake. I actually had one missing value, not sure why SPSS could not find it.

I would like to make sure that I test for measurement invariance the right way:

(1) I am running a CFA in each country separately, hoping that the model fit is sufficient in each country.

What is the easiest was to test for configural, metric and scalar invariance? Do I have to write a syntax for each country separately again or do I have one syntax including all countries?

Sorry for these very basic questions and thanks a lot for your help.
 Linda K. Muthen posted on Friday, July 30, 2010 - 4:18 pm
See the Topic 1 course handout under multiple group analysis.
 Linda Bode posted on Wednesday, August 04, 2010 - 2:04 am
One last question: Is there a rule of thumb about the required sample size to test for measurement invariance? And do you know a reference where I can read more about it?

Thanx a lot!
 Linda K. Muthen posted on Wednesday, August 04, 2010 - 6:35 am
I know of no rule of thumb for sample size. It depends on the model and the quality of the variables. You would need to do a Monte Carlo simulation study to understand the sample size needed for your particular study.
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: