Hello everybody,
I am running a confirmatory factor analysis, treating data as ordinal rather than continuous. I am therefore using robust weighted least squares estimator (WLSMV) based on the polychoric correlation matrix of latent continuous response variables. Since I am not able to produce any BIC and AIC, I was wondering what estimator I could use for model comparison. I read that in Mplus one could run a DIFFTEST. Does anyone know how to do it in JASP, Jamovi or SPSS?
Thank you very much!
Hi Tommaso, if your models are nested you can compare the chi-squared statistics by doing the calculation by hand or use an online calculator. Things are a lot more difficult if the models are not nested.
Cheers
Mark
I don't think you can have any model comparison in JASP or jamovi. Both programs use the lavaan package in the background to run CFA/SEM models. If you look up the lavaan package in R, the lavTestLRT function can be used for comparing multiple models.
Thank you a lot, much appreciated! I managed to run it in R, using the lavaan as well as the SBSDiff packages.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS