|
![](http://www.statmodel.com/discussion/icons/csc/1px.gif) |
Parameter estimate correlation |
![Previous](http://www.statmodel.com/discussion/icons/csc/navgen_arrow_left.gif) ![](http://www.statmodel.com/discussion/icons/csc/1px.gif)
|
Message/Author |
|
|
Hello, I have a CFA model with two factors and 12 binary indicators. I have fitted the model via WLSMV. I've been inspecting the correlation matrix of the parameter estimates and I have found some of the correlations to be very high (0.90). Are those values correct for binary indicators? How would you interpret this high correlations? Thank you very much |
|
|
Those two parameters are not clearly distinct. You may consider reducing the number of parameters. |
|
Back to top |
|
|