LEM: log-linear and event history analysis with missing data. Developed by Jeroen K. Vermunt (c), Tilburg University, The Netherlands. Version 1.2 (July 10, 1998). *** INPUT *** *data generated from rasch theta N(0,1) * Rasch MMLE man 4 lat 1 dim 9 2 2 2 2 lab X A B C D mod X {wei(X)} A|X {A} B|X {B} C|X {C} D|X {D} all {spe(XA,XB,XC,XD,1b)} sta wei(X) nor(1,8) nco data gen4rasch_normal.dat *** STATISTICS *** Number of iterations = 60 Converge criterion = 0.0000007604 Seed random values = 4682 X-squared = 0.0094 (1.0000) L-squared = 0.0094 (1.0000) Cressie-Read = 0.0094 (1.0000) Dissimilarity index = 0.0000 Degrees of freedom = 10 Log-likelihood = -2513556.09962 Number of parameters = 5 (+1) Sample size = 1000000.0 BIC(L-squared) = -138.1457 AIC(L-squared) = -19.9906 BIC(log-likelihood) = 5027181.2768 AIC(log-likelihood) = 5027122.1992 Eigenvalues information matrix 8.15E+0005 7.57E+0005 7.26E+0005 4.26E+0005 2.00E+0005 *** FREQUENCIES *** A B C D observed estimated std. res. 1 1 1 1 106140.150 106145.495 -0.016 1 1 1 2 129889.460 129877.042 0.034 1 1 2 1 64501.198 64494.511 0.026 1 1 2 2 139466.040 139481.917 -0.043 1 2 1 1 32030.347 32027.526 0.016 1 2 1 2 69256.785 69265.750 -0.034 1 2 2 1 34391.902 34396.077 -0.023 1 2 2 2 129889.460 129877.042 0.034 2 1 1 1 15905.800 15904.271 0.012 2 1 1 2 34391.902 34396.077 -0.023 2 1 2 1 17078.513 17080.449 -0.015 2 1 2 2 64501.198 64494.511 0.026 2 2 1 1 8480.939 8482.032 -0.012 2 2 1 2 32030.347 32027.526 0.016 2 2 2 1 15905.800 15904.271 0.012 2 2 2 2 106140.150 106145.495 -0.016 *** PSEUDO R-SQUARED MEASURES *** * P(A|X) * baseline fitted R-squared entropy 0.6061 0.5258 0.1325 qualitative variance 0.2077 0.1753 0.1563 classification error 0.2944 0.2671 0.0928 -2/N*log-likelihood 1.2121 1.0516 0.1325/0.1383 likelihood^(-2/N) 3.3607 2.8622 0.1483/0.2112 * P(B|X) * baseline fitted R-squared entropy 0.6828 0.5907 0.1349 qualitative variance 0.2448 0.2028 0.1715 classification error 0.4281 0.3116 0.2722 -2/N*log-likelihood 1.3656 1.1814 0.1349/0.1555 likelihood^(-2/N) 3.9179 3.2588 0.1682/0.2259 * P(C|X) * baseline fitted R-squared entropy 0.6828 0.5907 0.1349 qualitative variance 0.2448 0.2028 0.1715 classification error 0.4281 0.3116 0.2722 -2/N*log-likelihood 1.3656 1.1814 0.1349/0.1555 likelihood^(-2/N) 3.9179 3.2588 0.1682/0.2259 * P(D|X) * baseline fitted R-squared entropy 0.6061 0.5258 0.1325 qualitative variance 0.2077 0.1753 0.1563 classification error 0.2944 0.2671 0.0928 -2/N*log-likelihood 1.2121 1.0516 0.1325/0.1383 likelihood^(-2/N) 3.3607 2.8622 0.1483/0.2112 *** LOG-LINEAR PARAMETERS *** * TABLE XA [or P(A|X)] * effect beta std err z-value exp(beta) Wald df prob A 1 0.5250 0.0013 393.677 1.6905 2 -0.5250 0.5916 154981.43 1 0.000 * TABLE XB [or P(B|X)] * effect beta std err z-value exp(beta) Wald df prob B 1 0.1750 0.0012 142.993 1.1912 2 -0.1750 0.8395 20447.03 1 0.000 * TABLE XC [or P(C|X)] * effect beta std err z-value exp(beta) Wald df prob C 1 -0.1750 0.0012 -142.999 0.8395 2 0.1750 1.1912 20448.70 1 0.000 * TABLE XD [or P(D|X)] * effect beta std err z-value exp(beta) Wald df prob D 1 -0.5250 0.0013 -393.722 0.5916 2 0.5250 1.6905 155016.65 1 0.000 * ALL TABLES * effect beta std err z-value exp(beta) Wald df prob spe(XA,.,XD,1b) 1 1.0000 0.0022 460.331 2.7183 211904.20 1 0.000 *** LATENT CLASS OUTPUT *** X 1 X 2 X 3 X 4 X 5 X 6 X 7 X 8 0.0001 0.0044 0.0540 0.2420 0.3989 0.2420 0.0540 0.0044 A 1 0.9936 0.9829 0.9548 0.8859 0.7408 0.5125 0.2789 0.1246 A 2 0.0064 0.0171 0.0452 0.1141 0.2592 0.4875 0.7211 0.8754 B 1 0.9873 0.9661 0.9129 0.7941 0.5866 0.3430 0.1611 0.0660 B 2 0.0127 0.0339 0.0871 0.2059 0.4134 0.6570 0.8389 0.9340 C 1 0.9747 0.9340 0.8389 0.6570 0.4134 0.2059 0.0871 0.0339 C 2 0.0253 0.0660 0.1611 0.3430 0.5866 0.7941 0.9129 0.9661 D 1 0.9503 0.8754 0.7211 0.4875 0.2592 0.1141 0.0452 0.0171 D 2 0.0497 0.1246 0.2789 0.5125 0.7408 0.8859 0.9548 0.9829 X 9 0.0001 A 1 0.0497 A 2 0.9503 B 1 0.0253 B 2 0.9747 C 1 0.0127 C 2 0.9873 D 1 0.0064 D 2 0.9936 E = 0.5134, lambda = 0.1459