Confidence intervals and p-values not... PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
 Joćo Miguel Picoito posted on Monday, March 11, 2019 - 6:01 am
I am running a latent class analysis with covariates using the r3step method. My model has 4 classes and the sample size is 678.

In the output the confidence intervals and p-values are not coherent.

For example:
With reference class #1

Estimate= 3.541
S.E. = 1.526
Est/S.E.= 1.665
Two-tailed p-value = 0.096

When inspecting the confidence intervals:
C#2 1.167 1.522 1.743 3.541 7.194 8.240 10.745

I get a 95% CI of 1.522,8.240, so it is a significant result.

How can I interpret this?
Are the methods for computing the p-value and confidence intervals different?
 Bengt O. Muthen posted on Monday, March 11, 2019 - 5:24 pm
Please send your full output to Support along with your license number.
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message