|
Message/Author |
|
|
Dear Dr. Muthen, I’m analysing my data with structural equation modelling with Mplus for the first time and I have some general questions: Is it allowed to expect a mediation between two parallel observed mediators? Is it right to make a root transformation if I have a quadratic relationship between my mediator and my dependent variable (both observed variables)? And is it always necessary to make a transformation with my data if one of the preconditions isn’t fulfilled? How do I know about the model fit if my dependent variable is categorical? Because than I won’t get a chi-square. Is it allowed to look at the model fit without specifying that the dependent variable is categorical to look at the chi-square and only specify that the dependent variable ist categorical in a further step of analysis to look at the model results? Thanks a lot for your help. I’m looking forward to hearing from you. Yours sincerely, Isabelle |
|
|
Yes, parallel mediators are allowed. Yes, you can do a trasnforamtion. Absolute fit statistics are not available with categorical outcomes and maximum likelihood estimation. They are for weighted least squares. Use the default WLSMV estimator if you want fit statistics. |
|
Back to top |
|
|