forum.smartpls.com

Hi there,

it didn‘t get that clear to me. So, I have a model with two latent variables and approximately 26 - 32 indicators. Data of n = 50 for each group (2 groups) have been collected. Can I really examine measurement invariance of reflective models with MICOM and are results comparible with conventional model fit indices of cbsem?

Thanks in advances.

Best
Dave

Hi David,

I can’t give you an answer, but I had a similar question: reading Henseler et al’s (2014) article (Testing measurement invariance of composites using partial least squares) (this is worth reading David), the focus is on composites (I.e., the formative scales). If this is the case why are the results of the reflective scales also considered?

Many thanks,

Al.