1-1-1 model with level1 &level2 moder... PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 rui tao posted on Wednesday, October 16, 2019 - 1:58 am
Hi, I'm trying the model with the following syntax:


usevari = clus wi ub pp dp aga int;
cluster = clus;
WITHIN = pp wi dp int;
BETWEEN = aga;
missing =all(999);
DEFINE:
int =wi*dp;
CENTER pp wi dp (groupmean);
CENTER aga(grandmean);

ANALYSIS: TYPE = twolevel;
MODEL:
%WITHIN%

dp on pp(a);
ub on dp(b);
ub on int(c);
ub on wi pp;

%BETWEEN%
ub on aga;

MODEL CONSTRAINT:
new(s_high s_low);
s_high=a*(b+c*1.83);
s_low=a*(b+c*0.83);

I want to test whether wi moderates the path from dp to ub and the result says yes (the model fits badly though,CFI=0.647,RMSEA=0.148), but the prompt keeps appearing as followed:

THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES MAY NOT BE
TRUSTWORTHY FOR SOME PARAMETERS DUE TO A NON-POSITIVE DEFINITE
FIRST-ORDER DERIVATIVE PRODUCT MATRIX. THIS MAY BE DUE TO THE STARTING
VALUES BUT MAY ALSO BE AN INDICATION OF MODEL NONIDENTIFICATION. THE
CONDITION NUMBER IS 0.276D-21. PROBLEM INVOLVING THE FOLLOWING PARAMETER:
Parameter 1, %WITHIN%: [ DP ]

Not sure whether I am getting this right, can anyone tell me if there's anything wrong with my syntax and if yes, how shall I correct it?
 Bengt O. Muthen posted on Wednesday, October 16, 2019 - 4:45 pm
We need to see your full output - send to Support@statmodel.com 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: