Multilevel MIRT random item effects m... PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 Shanshan Wang posted on Tuesday, June 30, 2015 - 9:54 pm
Hi Dr. Muthen,

I tried to fit a MMIRT random item effects model to the PISA student achievement data. The error message I received is as follows:

THE MODEL ESTIMATION DID NOT TERMINATE NORMALLY.
THE PSI MATRIX IS NOT POSITIVE DEFINITE.

THE PROBLEM OCCURRED IN CHAIN 2.

PROBLEM INVOLVING VARIABLES U1 AND  .

THE PROBLEM OCCURRED ON THE WITHIN LEVEL.

Will you please tell me why the model didn't work?

Thank you!
SW

Data:
File is pisa12book7a_math_short.csv;
Variable:
Names are counid stid u1 u2 u3 u4 u5 u6 u7 u8 u9 u10 u11;
Usevariables = u1-u11;
Missing are all (7,8,9);
Categorical = u1-u11;
Cluster = counid;
Analysis:
Type = twolevel random;
Process = 2;
Estimator = bayes;
Thin = 100;
Model:
%within%
s11-s16|f1 by u2* u3 u6 u8 u9 u10;
s21-s23|f2 by u4* u5 u6;
s31-s34|f3 by u1* u2 u7 u11;
f1-f3@1;
%between%
f1 u2 u3 u6 u8 u9 u10 s11-s16;
f2 u4 u5 u6 s21-s23;
f3 u1 u2 u7 u11 s31-s34;
Output:
tech1 tech8 stdy;
 Bengt O. Muthen posted on Wednesday, July 01, 2015 - 5:22 pm
Please send output and data to support along with your license number
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: