MONTECARLO INTEGRATION AND CONFIDENCE... PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 emmanuel bofah posted on Monday, February 01, 2016 - 2:59 am
Hi Prof,
If you used ANALYSIS: ESTIMATOR = MLR; INTEGRATION = MONTECARLO;
Does the confidence interval construction has the property that are not assumed to be normally distributed (or even symmetric)?
 Linda K. Muthen posted on Monday, February 01, 2016 - 11:06 am
Please send the output you are asking about and your license number to support@statmodel.com.
 emmanuel bofah posted on Monday, February 01, 2016 - 11:12 am
Dear Linda,
I am just asking if you used ANALYSIS: ESTIMATOR = MLR; INTEGRATION = MONTECARLO; and request for confidence interval does the confidence interval assumed to be normally distributed (or symmetric)? However i have send this same question with my license number.
 Linda K. Muthen posted on Monday, February 01, 2016 - 2:12 pm
The CINTERVAL option gives symmetric confidence intervals as the default.
 Nicole Kratky posted on Wednesday, June 06, 2018 - 10:10 pm
Dear Linda and Bengt,

I am running a multilevel moderation analysis and I want to use the Montecarlo confidence intervals for the indirect effect.
Can you please tell me which kind of command I have to use and if it is right to put it in the ANALYSIS area after the TYPE=TWOLEVEL command? I have tried INTEGRATION=MONTECARLO but it wasn't working.
Thank you a lot!
 Bengt O. Muthen posted on Thursday, June 07, 2018 - 4:15 pm
Mplus does not produce "Montecarlo CIs". I think you want non-symmetric CIs and for the multilevel case this is obtained by using Estimator = Bayes.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: