Why no clustered SEs option in SEM?!
There doesn't seem to be the option to use clustered standard errors in the structural equation modeling analysis (SEM module). Is there a reason for this? In lavaan it's as simple as adding cluster="varname" in the call to cfa() or sem() or lavaan().
Comments
I've asked our expert (who is on vacation)
Maybe more of a feature request for the GitHub page?
EJ
OK done. I also encountered a bug in the R console trying to run the analysis through the R console, so I filed a bug report too😭😭
You can always link to the GitHub issue here, so people who care can track progress...
Feature request for clustered SEs in SEM: https://github.com/jasp-stats/jasp-issues/issues/4504
Bug report for console that gets confused when variable names overlap with R syntax: https://github.com/jasp-stats/jasp-issues/issues/4503
As for the bug, Shun has already fixed at least part of it (I don't know if it's all fixed yet), so it may or may not be fixed in the next update (the one after 0.98.1)