SEM: the fitted*model is not full rank

[CE Beaudoin]

Hello:

Across 10 years or so, I used different versions of Stata regularly. Then, I didn't use Stata at all across three years as an administrator. Now, back to my normal position, I'm trying to refresh my capacity to use Stata, currently, in particular, SEM. For some trials with a dataset, I keep getting this indication: "Note: The LR test of model vs. saturated is not reported because the fitted model is not full rank." (I don't recall every seeing this in my prior SEM work with Stata.)

I have searched about in Statalist and elsewhere on the web. There are assorted posts about this, but I can't find a clear explanation of why this indication appears, what it may mean, and how one can alter a dataset or model to address it.

Thanks for any help with this.

Chris

[CE Beaudoin]

Aha, I figured it out by playing about with one variable and recoding it. Pardon the start of this thread.

[Alamsyah Alamsyah]

Hello:

Across 10 years or so, I used different versions of Stata regularly. Then, I didn't use Stata at all across three years as an administrator. Now, back to my normal position, I'm trying to refresh my capacity to use Stata, currently, in particular, SEM. For some trials with a dataset, I keep getting this indication: "Note: The LR test of model vs. saturated is not reported because the fitted model is not full rank." (I don't recall every seeing this in my prior SEM work with Stata.)

I have searched about in Statalist and elsewhere on the web. There are assorted posts about this, but I can't find a clear explanation of why this indication appears, what it may mean, and how one can alter a dataset or model to address it.

Thanks for any help with this.

Chris

I have the same problem. Did you solve this problem? Would you share the tips, please?