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 *** * LSAT 7 data * MMLE of 2PL model * man 5 lat 1 dim 9 2 2 2 2 2 lab X A B C D E mod X {wei(X)} A|X {A spe(A,1a,X,c,-1)} B|X {B spe(B,1a,X,c,-1)} C|X {C spe(C,1a,X,c,-1)} D|X {D spe(D,1a,X,c,-1)} E|X {E spe(E,1a,X,c,-1)} sta wei(X) [0.000022345844 0.002789141321 0.049916406765 0.244097502895 0.406349206349 0.244097502895 0.049916406765 0.002789141321 0.000022345844] des [ -4.512745863399 -3.205429002856 -2.076847978677 -1.023255663789 0.000000000000 1.023255663789 2.076847978677 3.205429002856 4.512745863399 -4.512745863399 -3.205429002856 -2.076847978677 -1.023255663789 0.000000000000 1.023255663789 2.076847978677 3.205429002856 4.512745863399 -4.512745863399 -3.205429002856 -2.076847978677 -1.023255663789 0.000000000000 1.023255663789 2.076847978677 3.205429002856 4.512745863399 -4.512745863399 -3.205429002856 -2.076847978677 -1.023255663789 0.000000000000 1.023255663789 2.076847978677 3.205429002856 4.512745863399 -4.512745863399 -3.205429002856 -2.076847978677 -1.023255663789 0.000000000000 1.023255663789 2.076847978677 3.205429002856 4.512745863399 ] ite 150000 nco data lsat7_dat.txt *** STATISTICS *** Number of iterations = 170 Converge criterion = 0.0000009723 Seed random values = 1647 X-squared = 32.4517 (0.0527) L-squared = 31.6688 (0.0632) Cressie-Read = 31.8736 (0.0603) Dissimilarity index = 0.0454 Degrees of freedom = 21 Log-likelihood = -2658.78923 Number of parameters = 10 (+1) Sample size = 1000.0 BIC(L-squared) = -113.3941 AIC(L-squared) = -10.3312 BIC(log-likelihood) = 5386.6560 AIC(log-likelihood) = 5337.5785 Eigenvalues information matrix 850.1060 749.4757 663.2680 630.4620 363.7773 240.9172 149.9596 132.8744 98.2641 28.2600 *** FREQUENCIES *** A B C D E observed estimated std. res. 1 1 1 1 1 12.000 10.089 0.602 1 1 1 1 2 19.000 18.468 0.124 1 1 1 2 1 1.000 4.500 -1.650 1 1 1 2 2 7.000 10.672 -1.124 1 1 2 1 1 3.000 4.948 -0.876 1 1 2 1 2 19.000 15.922 0.771 1 1 2 2 1 3.000 3.964 -0.484 1 1 2 2 2 17.000 16.431 0.140 1 2 1 1 1 10.000 3.937 3.056 1 2 1 1 2 5.000 10.355 -1.664 1 2 1 2 1 3.000 2.558 0.276 1 2 1 2 2 7.000 8.612 -0.549 1 2 2 1 1 7.000 4.404 1.237 1 2 2 1 2 23.000 20.382 0.580 1 2 2 2 1 8.000 5.149 1.257 1 2 2 2 2 28.000 31.612 -0.642 2 1 1 1 1 7.000 12.765 -1.614 2 1 1 1 2 39.000 32.589 1.123 2 1 1 2 1 11.000 8.041 1.043 2 1 1 2 2 34.000 26.278 1.506 2 1 2 1 1 14.000 13.322 0.186 2 1 2 1 2 51.000 59.692 -1.125 2 1 2 2 1 15.000 15.059 -0.015 2 1 2 2 2 90.000 89.255 0.079 2 2 1 1 1 6.000 8.079 -0.732 2 2 1 1 2 25.000 29.276 -0.790 2 2 1 2 1 7.000 7.323 -0.119 2 2 1 2 2 35.000 34.475 0.089 2 2 2 1 1 18.000 19.442 -0.327 2 2 2 1 2 136.000 130.323 0.497 2 2 2 2 1 32.000 33.417 -0.245 2 2 2 2 2 308.000 308.660 -0.038 *** PSEUDO R-SQUARED MEASURES *** * P(A|X) * baseline fitted R-squared entropy 0.4590 0.4019 0.1244 qualitative variance 0.1424 0.1250 0.1223 classification error 0.1720 0.1654 0.0382 -2/N*log-likelihood 0.9181 0.8039 0.1244/0.1025 likelihood^(-2/N) 2.5045 2.2342 0.1079/0.1797 * P(B|X) * baseline fitted R-squared entropy 0.6424 0.5456 0.1506 qualitative variance 0.2250 0.1838 0.1833 classification error 0.3420 0.2727 0.2026 -2/N*log-likelihood 1.2847 1.0912 0.1506/0.1621 likelihood^(-2/N) 3.6136 2.9780 0.1759/0.2432 * P(C|X) * baseline fitted R-squared entropy 0.5368 0.3886 0.2762 qualitative variance 0.1760 0.1235 0.2981 classification error 0.2280 0.1905 0.1647 -2/N*log-likelihood 1.0737 0.7771 0.2762/0.2288 likelihood^(-2/N) 2.9262 2.1751 0.2567/0.3899 * P(D|X) * baseline fitted R-squared entropy 0.6705 0.6121 0.0871 qualitative variance 0.2388 0.2121 0.1118 classification error 0.3940 0.3310 0.1600 -2/N*log-likelihood 1.3410 1.2243 0.0871/0.1045 likelihood^(-2/N) 3.8229 3.4017 0.1102/0.1492 * P(E|X) * baseline fitted R-squared entropy 0.4347 0.4024 0.0741 qualitative variance 0.1324 0.1233 0.0685 classification error 0.1570 0.1563 0.0046 -2/N*log-likelihood 0.8693 0.8049 0.0741/0.0605 likelihood^(-2/N) 2.3853 2.2365 0.0624/0.1074 *** LOG-LINEAR PARAMETERS *** * TABLE XA [or P(A|X)] * effect beta std err z-value exp(beta) Wald df prob A 1 -0.9284 0.0659 -14.097 0.3952 2 0.9284 2.5304 198.72 1 0.000 spe(A,1a) [X 1] 1 0.4946 0.0888 5.569 1.6399 31.01 1 0.000 * TABLE XB [or P(B|X)] * effect beta std err z-value exp(beta) Wald df prob B 1 -0.4041 0.0456 -8.857 0.6676 2 0.4041 1.4979 78.44 1 0.000 spe(B,1a) [X 1] 1 0.5406 0.0844 6.402 1.7170 40.99 1 0.000 * TABLE XC [or P(C|X)] * effect beta std err z-value exp(beta) Wald df prob C 1 -0.9027 0.1026 -8.800 0.4055 2 0.9027 2.4663 77.44 1 0.000 spe(C,1a) [X 1] 1 0.8530 0.1594 5.351 2.3467 28.63 1 0.000 * TABLE XD [or P(D|X)] * effect beta std err z-value exp(beta) Wald df prob D 1 -0.2430 0.0375 -6.489 0.7843 2 0.2430 1.2751 42.11 1 0.000 spe(D,1a) [X 1] 1 0.3824 0.0670 5.706 1.4658 32.56 1 0.000 * TABLE XE [or P(E|X)] * effect beta std err z-value exp(beta) Wald df prob E 1 -0.9274 0.0572 -16.204 0.3956 2 0.9274 2.5279 262.57 1 0.000 spe(E,1a) [X 1] 1 0.3682 0.0756 4.868 1.4451 23.70 1 0.000 *** LATENT CLASS OUTPUT *** X 1 X 2 X 3 X 4 X 5 X 6 X 7 X 8 0.0000 0.0028 0.0499 0.2441 0.4063 0.2441 0.0499 0.0028 A 1 0.0018 0.0065 0.0196 0.0537 0.1351 0.3006 0.5493 0.7882 A 2 0.9982 0.9935 0.9804 0.9463 0.8649 0.6994 0.4507 0.2118 B 1 0.0034 0.0137 0.0451 0.1285 0.3083 0.5740 0.8080 0.9345 B 2 0.9966 0.9863 0.9549 0.8715 0.6917 0.4260 0.1920 0.0655 C 1 0.0001 0.0007 0.0047 0.0279 0.1412 0.4851 0.8504 0.9750 C 2 0.9999 0.9993 0.9953 0.9721 0.8588 0.5149 0.1496 0.0250 D 1 0.0191 0.0503 0.1116 0.2195 0.3808 0.5736 0.7507 0.8771 D 2 0.9809 0.9497 0.8884 0.7805 0.6192 0.4264 0.2493 0.1229 E 1 0.0056 0.0146 0.0328 0.0686 0.1353 0.2495 0.4193 0.6237 E 2 0.9944 0.9854 0.9672 0.9314 0.8647 0.7505 0.5807 0.3763 X 9 0.0000 A 1 0.9313 A 2 0.0687 B 1 0.9832 B 2 0.0168 C 1 0.9973 C 2 0.0027 D 1 0.9510 D 2 0.0490 E 1 0.8127 E 2 0.1873 E = 0.4810, lambda = 0.1898