Saturated model PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 Jonathon Little posted on Wednesday, June 24, 2015 - 8:53 am
In the model below the between-level is saturated (df=0) yet returns a between-level SRMR of .036 - it should be 0.00.

ANALYSIS:
TYPE= TWOLEVEL RANDOM;
ESTIMATOR = MLR;
H1ITERATIONS = 10000;

MODEL:
%BETWEEN%
T1K_1 WITH T1K_2;
T1K_1 -T1K_2 WITH T1K_3;
T1K_1 -T1K_3 WITH T1K_4;
T1K_1 -T1K_4 WITH T1K_5;

T1K_1 - T1K_5;

%WITHIN%
F1 BY T1K_1 -T1K_5;
T1K_1 - T1K_5;

Am I missing something hear? Is a saturated between-level model not possible with MLR (or even BAYES for that matter)???
 Tihomir Asparouhov posted on Thursday, June 25, 2015 - 8:22 am
In ML SW(Sigma-within) and SB(Sigma-between) are not fitted independently of each other. Restrictions on the within level could affect the estimates on the between. You can use the residual output option for more information.
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: