paul-buerkner / thurstonianIRT

Fit Thurstonian IRT models in R using Stan, lavaan, or Mplus
GNU General Public License v3.0
31 stars 12 forks source link

Latent Trait Estimates Appearing as NA with Lavaan Fitting #31

Open rahulpatel1936 opened 2 years ago

rahulpatel1936 commented 2 years ago

Hello everyone,

I have a dataset where each column is an item, housed within their respective block (24 blocks, each with 4 items); the responses are in the form of ranks, where higher values denote more desired choices. This issue is that upon running the T-IRT in R using the fit_TIRT_lavaan command, the run-time for R to execute the code is too long to the point where I have to stop the code from executing—is this to be expected?

I tried running the model with 5 blocks instead of 24, and while the code was executed, I encountered some error messages and was not able to recover the latent trait scores as they appeared as NA—has anyone had this issue and has come up with a solution? I'm happy to share my code if it helps