|
|
NON-POSITIVE DEFINITE MATRIX |
|
Message/Author |
|
M.O. posted on Monday, January 26, 2015 - 5:39 pm
|
|
|
Dear Dr Muthen, I am conducting simple mixture analysis on categorical data. My input statement is: ----- TITLE: LCA DATA: FILE = '35itemN888.dat'; VARIABLE: NAMES = u1-u35; CATEGORICAL = u1-u35; CLASSES = C(3); ANALYSIS: TYPE IS MIXTURE; STARTS = 1000 100; STITERATIONS = 50; ---------- I receive warning message as follows. I suspect I should not use this solution? Can I do anything to deal with this problem? ----- 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 0.569D-10. PROBLEM INVOLVING THE FOLLOWING PARAMETER: Parameter 420, %C#3%: [ U35$4 ] ------ Thank you for your help, |
|
|
This message should not be ignored. Please send the output and your data to support@statmodel.com. |
|
Back to top |
|
|