Message/Author |
|
|
I am a doctoral student. For the purpose of my thesis I am trying to estimate a two-wave longitudinal model using SEM. I am using LISREL for the purpose. Please find the code attached here below. My problem is though I am getting good fit indices (Goodness of Fit Index (GFI) = 0.93; Adjusted Goodness of Fit Index (AGFI) = 0.90; Minimum Fit Function Chi-Square = 47.92 (P = 0.97); P-Value for Test of Close Fit (RMSEA < 0.05) = 1.00), I am getting the following warning which I have not been able to resolve: W_A_R_N_I_N_G: PH 3,1 may not be identified. Standard Errors, T-Values, Modification Indices,and Standardized Residuals cannot be computed. W_A_R_N_I_N_G: The solution has not converged after 250 iterations.The following solution is preliminary and is provided only for the purpose of tracing the source of the problem. Setting IT>250 may solve the problem. I had to use the RC option because initially the THETA-EPS matrix was not positive definite. I would be extremely grateful to you if you can kindly help me in resolving the issue. Warm Regards -Anirban Chakraborty Code: TI Ext DA NI=14 NO=106 NG=1 MA=KM RA FI='C:\Documents and Settings\Administrator\Desktop\Ext.psf' MO NX=6 NY=8 NK=3 NE=5 LY=FU,FI LX=FU,FI BE=FU,FI GA=FU,FI PH=SY,FR PS=DI,FR TE=SY,FI TD=SY,FI SE 7 8 9 10 11 12 13 14 1 2 3 4 5 6 / LK PJ1 IJ1 RE1 LE SAT1 PJ2 IJ2 RE2 SAT2 FR LX(1,1) LX(2,1) LX(3,2) LX(4,2) LX(5,2) LX(6,3) LY(1,1)LY(2,2) LY(3,2) LY(4,3) LY(5,3) LY(6,3) LY(7,4) LY(8,5) GA(1,1) GA(1,2) GA(1,3) BE(5,1) BE(5,2) BE(5,3) BE(5,4) TD(1,1) TD(2,2) TD(3,3) TD(4,4) TD(5,5) TE(2,2) TE(3,3) TE(4,4) TE(5,5) TE(6,6); VALUE 0.3 TD(6,6); VALUE 0.3 TE(1,1) TE(7,7) TE(8,8) ST 0.7 LY(1,1)LY(2,2) LY(3,2) LY(4,3) LY(5,3) LY(6,3) LY(7,4) LY(8,5) ST 0.5 LX(1,1) LX(2,1) LX(3,2) LX(4,2) LX(5,2) LX(6,3) ST 0.9 TD(1,1) TD(2,2) TD(3,3) TD(4,4) TD(5,5) TE(2,2) TE(3,3) TE(4,4) TE(5,5) TE(6,6) PD OU SE TV RS RC=.85 RO SS MI ME=GLS IT=250 |
|
|
You will need to send your question to LISREL support. |
|
Back to top |
|