Attachment | Size |
---|---|
Saturated_Beta_OpenMx.R [6] | 15.31 KB |
Hi,
I am trying to fit a saturated twin model to 9 ordinal variables (representing age at observation), in which participants have either 1, 2 or 3 observations each. Thus, there is quite a bit of missing data.
When running the model I get the following error: Sat5.fitfunction is not finite.
Here is info about version and platform:
OpenMx version: 2.0.1.4157
R version: R version 3.1.1 (2014-07-10)
Platform: x86_64-w64-mingw32
Default optimiser: NPSOL
Does this mean that there could be a problem due to too many NA’s in the data? I expected FIML to take care of this. I saw another thread #3940 about the same issue, but couldn’t really cut out what was causing the error.
I tried the CSOLNP optimizer and mxTryHard() with the same result. Could it be bad starting values that’s causing the error in my case?
When running it in OpenMx1.4-3060 I get the following error message: Objective function returned a value of NaN at iteration 23.63.
I have attached the script in case that helps to clarify anything.
Many thanks,
Karoline