Negative residual variance message? PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Steven Kamper posted on Tuesday, November 26, 2013 - 1:55 am
Hi,
I am trying to run CFAs with 2 and 3 factors and 14 indicators. I get the following warning message:

WARNING: THE RESIDUAL COVARIANCE MATRIX (THETA) IS NOT POSITIVE DEFINITE. THIS COULD INDICATE A NEGATIVE VARIANCE/RESIDUAL VARIANCE FOR AN OBSERVED VARIABLE, A CORRELATION GREATER OR EQUAL TO ONE BETWEEN TWO OBSERVED VARIABLES, OR A LINEAR DEPENDENCY AMONG MORE THAN TWO OBSERVED VARIABLES. CHECK THE RESULTS SECTION FOR MORE INFORMATION. PROBLEM INVOLVING VARIABLE IPQ3.

And the following estimates in the R2 section of the output:

Observed Two-Tailed Residual
Variable Estimate S.E. Est./S.E. P-Value Variance

IPQ2 0.861 0.037 23.474 0.000 0.139
IPQ3 Undefined 0.10324E+01 -0.032

I understand that there is a problem with my IPQ3 variable, but I am not sure what it is or what I should do to solve the issue. I'd be grateful for any help.
 Linda K. Muthen posted on Tuesday, November 26, 2013 - 6:05 am
You have a negative residual variance for IPQ3. This makes the model inadmissible. For a continuous variable, if the value is small and insignificant, you can fix the residual variance to zero. With a categorical item, the residual variance is not a model parameter so you can't fix the residual variance to zero. You need to change the model or not use that item.
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: