Dear Professors Muthen, I was wondering how precisely the 'Probability RMSEA<-0.05' is computed? It seems to be based on the range of the 90% confidence interval, but a recent paper shows that confidence intervals cannot be used to compute the probability of the parameter. Rather, the procedure itself will generate a CI that contains the true value of the parameter 90% of the time (similar but different). This probably rarely makes a difference so I'm not trying to make a pedantic correction, but rather I want make sure I am making the correct claims regarding the RMSEA probability (according to Morey et al. al Bayesian credible interval would allow for the desired interpretation, but perhaps that is what you are using already?).
The reference is: Morey, Richard D., Rink Hoekstra, Jeffrey N. Rouder, Michael D. Lee, and Eric-Jan Wagenmakers. "The Fallacy of Placing Confidence in Confidence Intervals." (2015).