With great interest I have read your article “How to us a monte carlo study to decide on sample size and determine power”. At the moment I am running a montecarlo simulation for my own model and since it contains categorical variables, I have used the method and syntax offered by Myers et al. I have adapted the syntax to my own model, everything works fine and I get a decent power.
However, one of the models that I am studying, is a bifactor model. I would also like to run a montecarlo simulation the bifactor model, but I struggle with the thoughts the possibility of running a simulation and the interpretation of it. In a bifactor model all the factors are forced to be orthogonal, therefore how would I interpret the power? (Since in the analysis of a correlated model one looks at the % sig column for the correlating factors.)
Therefore I would like to ask you whether you think it is possible to run a power-estimation montecarlo simulation for a bifactor model that contains categorical variables. And if it would be possible, how would one interpret its power? Thank you in advance for answering these questions.