I guess this is a pretty basic question, but I can't find this in the manual for IRT (Item Response Theory) for Stata 14.
I have been using the new IRT command to generate a 2PL Item Response Theory model, based on binary items (rather than using the -gsem- command, because shiny new IRT in Stata 14!).
There are postestimation commands for comparing model fit for nested models, i.e. to a 1PL model, using a lrtest. However, I can't seem to figure out how to obtain general test results of how the model fits the data, - ie the typical RMSEA, CFI/TLI, and Chi-squared tests applied in MPlus. I might be missing an obvious command. Would rather not have to convert everything over to Mplus! Does anyone know if these functions are available in Stata 14, or if some other packages can be applied to do this?
I have been using the new IRT command to generate a 2PL Item Response Theory model, based on binary items (rather than using the -gsem- command, because shiny new IRT in Stata 14!).
There are postestimation commands for comparing model fit for nested models, i.e. to a 1PL model, using a lrtest. However, I can't seem to figure out how to obtain general test results of how the model fits the data, - ie the typical RMSEA, CFI/TLI, and Chi-squared tests applied in MPlus. I might be missing an obvious command. Would rather not have to convert everything over to Mplus! Does anyone know if these functions are available in Stata 14, or if some other packages can be applied to do this?
Comment