|
|
Non-positive product matrix |
|
Message/Author |
|
|
Hi, I'm trying to run a FMM but kept running into a problem that I cannot resolve. 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 0.258D-12. PROBLEM INVOLVING PARAMETER 1. What's the problem with my syntax? Variable: names are id u1 u2 u3 u4 u5 u6 u7 u8 u9 u10 u11 u12 u13 u14 u15; idvariable is id; usevar = u1 u2 u3 u4 u5 u6 u7 u8 u9 u10 u11 u12 u13 u14 u15; classes = c(2); Analysis: type = mixture; starts = 1000 100; Processors = 4(starts); Model: %Overall% f1 BY u3 u4 u5 u8; f2 BY u6 u7 u9 u10 u11 u13 u14; f3 BY u1 u2 u12 u15; [f1-f3@0]; %c#1% f1-f3; f1 BY u4 u5 u8; f2 BY u7 u9 u10 u11 u13 u14; f3 BY u2 u12 u15; f1 with f2; f1 with f3; f2 with f3; [u1-u15]; %c#2% f1-f3; f1 BY u4 u5 u8; f2 BY u7 u9 u10 u11 u13 u14; f3 BY u2 u12 u15; f1 with f2; f1 with f3; f2 with f3; [u1-u15]; Thank you so much for your help. |
|
|
Please send the output and your license number to support@statmodel.com. |
|
Back to top |
|
|