I'm currently exploring the possibility of using Mplus in my thesis to undertake SEM and wanted to check if my proposed analysis was possible before purchasing the software.
I'm looking at the relationship between family structure and child well-being.
1. My predictor variable is family type consisting of 3 categories - am I right in thinking I would create dummy variables to enter this into my model?
2. I have 3 mediating variables. One is an observed continuous variable (a measure of maternal mental health) the other two are latent variables ('parenting behaviours' and 'household economic circumstances')both of which consist of continuous, ordered categorical and binary observed indicators - can Mplus handle this mixture of variables in the context of latent mediating variables?
3. My outcome is a latent variable 'child well-being' which in turn consists of 4 latent variables representing 4 domains of child well-being. These 4 domains of child well-being consist of a mixture of continuous, ordered categorical and binary observed indicators. My understanding is that Mplus can handle this mixture of outcome variables?
I hope the explanation of my proposed model is clear enough and many thanks in advance for your help.