|
|
ML vs. WLSMV (moderated mediation)... |
|
Message/Author |
|
Jay O'Toole posted on Thursday, November 14, 2013 - 11:45 am
|
|
|
I am running a moderated mediation model consistent with Preacher et al. (2007) model 2. I am following the MPlus code posted by Andrew Hayes. I have been trying to figure out why I am getting such divergent results between using a ML estimator and a WLSMV estimator and bias corrected bootstrapped confidence intervals. I am hoping you can help me better understand why the results might be so different and suggest a few references for me to consider. Thanks. |
|
Jay O'Toole posted on Thursday, November 14, 2013 - 11:54 am
|
|
|
Sorry, I should have also stated that the model DV is binary and the mediator a continous latent variable. |
|
|
Please send the two outputs and your license number to support@statmodel.com. |
|
Jay O'Toole posted on Tuesday, November 19, 2013 - 9:27 am
|
|
|
thanks. will do. |
|
Back to top |
|
|