Savedata output PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Shanshan Wang posted on Wednesday, March 18, 2015 - 11:51 am
Hi Mplus veterans!

I ran a Two-Level Random Loadings IRT model.

TITLE: RANp1
DATA: FILE = ...
NAMES =
id group y1-y5;
USEVARIABLES =
group y1-y5;
CATEGORICAL =
y1-y5;
CLUSTER =
group;
ANALYSIS:
ESTIMATOR = BAYES;
PROCESSORS = 2;
BSEED = 48932;
BCONVERGENCE = .05;
TYPE = TWOLEVEL RANDOM;
Biterations = 50000000(1000);
MODEL:
%WITHIN%
s1-s5 | f BY y1-y5; f@1; ;
%between%
f; y1-y5(v1-v5);
s1-s5(v6-v10);
MODEL PRIORS: v1-v5 ~ N(1, 0.09);
v6-v10 ~ N(0, 1);
OUTPUT:
TECH1 TECH8;
SAVEDATA:
FILE=...;
SAVE=FS(50); FACTORS=f;

In the savedata output, I got the following variables:
y1 -y5
F%W (mean, median, std, 2.5%, 97.5%)
F%B (mean, median, std, 2.5%, 97.5%)
S1-S5 (mean, median, std, 2.5%, 97.5%)
B_Y1-B_Y5 (mean, median, std, 2.5%, 97.5%).

Is S1 the between level lambda value? Is B_Y1 the between level tau value? Or are they deviations from the mean?

How can I obtain group specific lambda and tau values?

Thank you!
SW
 Bengt O. Muthen posted on Wednesday, March 18, 2015 - 4:38 pm
S1-S5 are the factor scores for the random slopes (loadings) and B_Y1 etc are the between-level random intercepts of the y variables. So they are the group-specific values of lambda and tau (actually minus tau) that you ask about. If you add them to your FACTORS= statement you will obtain them all.
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: