* * * * * * * * * * * * * * * * * * * * * H I E R A R C H I C A L L O G L I N E A R * * * * * * * * * * * * * * * * * * * * * DATA Information 1335 unweighted cases accepted. 0 cases rejected because of out-of-range factor values. 165 cases rejected because of missing data. 1335 weighted cases will be used in the analysis. FACTOR Information Factor Level Label APBEFISK 5 apa befejezett iskolai végzettsé BEFISK 5 iskolaoszevont NEME 2 49.01.A kérdezett neme TARSCSOP 3 társadalmi csoport hovatartozás VALLAS 5 Milyen vallásba van bejegyezve - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - * * * * * * * * * * * * * * * * * * * * * H I E R A R C H I C A L L O G L I N E A R * * * * * * * * * * * * * * * * * * * * * DESIGN 1 has generating class APBEFISK*BEFISK*NEME*TARSCSOP*VALLAS Note: For saturated models ,500 has been added to all observed cells. This value may be changed by using the CRITERIA = DELTA subcommand. The Iterative Proportional Fit algorithm converged at iteration 1. The maximum difference between observed and fitted marginal totals is ,000 and the convergence criterion is ,250 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Goodness-of-fit test statistics Likelihood ratio chi square = ,00000 DF = 0 P = 1,000 Pearson chi square = ,00000 DF = 0 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Tests that K-way and higher order effects are zero. K DF L.R. Chisq Prob Pearson Chisq Prob Iteration 5 128 9,373 1,0000 8,419 1,0000 5 4 416 93,881 1,0000 91,975 1,0000 6 3 648 285,698 1,0000 331,053 1,0000 7 2 734 1216,009 ,0000 6350,370 ,0000 2 1 749 5887,120 ,0000 18179,046 ,0000 0 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Tests that K-way effects are zero. K DF L.R. Chisq Prob Pearson Chisq Prob Iteration 1 15 4671,111 ,0000 11828,676 ,0000 0 2 86 930,310 ,0000 6019,317 ,0000 0 3 232 191,818 ,9747 239,078 ,3609 0 4 288 84,508 1,0000 83,557 1,0000 0 5 128 9,373 1,0000 8,419 1,0000 0 >Note # 13865 >DF used for these tests have NOT been adjusted for structural or sampling >zeros. Tests using these DF may be conservative. * * * * * * * * * * * * * * * * * * * * * H I E R A R C H I C A L L O G L I N E A R * * * * * * * * * * * * * * * * * * * * * Tests of PARTIAL associations. Effect Name DF Partial Chisq Prob Iter APBEFISK*BEFISK*NEME*TARSCSOP 32 22,984 ,8788 4 APBEFISK*BEFISK*NEME*VALLAS 64 21,262 1,0000 5 APBEFISK*BEFISK*TARSCSOP*VALLAS 128 7,580 1,0000 6 APBEFISK*NEME*TARSCSOP*VALLAS 32 5,516 1,0000 5 BEFISK*NEME*TARSCSOP*VALLAS 32 15,248 ,9946 4 APBEFISK*BEFISK*NEME 16 25,486 ,0617 6 APBEFISK*BEFISK*TARSCSOP 32 28,701 ,6343 5 APBEFISK*NEME*TARSCSOP 8 9,053 ,3379 6 BEFISK*NEME*TARSCSOP 8 16,818 ,0321 6 APBEFISK*BEFISK*VALLAS 64 36,266 ,9980 5 APBEFISK*NEME*VALLAS 16 15,459 ,4913 6 BEFISK*NEME*VALLAS 16 23,596 ,0987 6 APBEFISK*TARSCSOP*VALLAS 32 11,290 ,9997 5 BEFISK*TARSCSOP*VALLAS 32 23,555 ,8601 5 NEME*TARSCSOP*VALLAS 8 3,035 ,9322 5 APBEFISK*BEFISK 16 183,067 ,0000 5 APBEFISK*NEME 4 2,117 ,7143 7 BEFISK*NEME 4 67,245 ,0000 6 APBEFISK*TARSCSOP 8 41,793 ,0000 6 BEFISK*TARSCSOP 8 263,688 ,0000 5 NEME*TARSCSOP 2 9,252 ,0098 6 APBEFISK*VALLAS 16 54,013 ,0000 7 BEFISK*VALLAS 16 16,398 ,4255 7 NEME*VALLAS 4 ,339 ,9872 7 TARSCSOP*VALLAS 8 7,843 ,4489 7 APBEFISK 4 1385,075 ,0000 2 BEFISK 4 107,605 ,0000 2 NEME 1 29,774 ,0000 2 TARSCSOP 2 863,884 ,0000 2 VALLAS 4 2284,770 ,0000 2 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - * * * * * * * * * * * * * * * * * * * * * H I E R A R C H I C A L L O G L I N E A R * * * * * * * * * * * * * * * * * * * * * Backward Elimination (p = ,050) for DESIGN 1 with generating class APBEFISK*BEFISK*NEME*TARSCSOP*VALLAS Likelihood ratio chi square = ,00000 DF = 0 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If Deleted Simple Effect is DF L.R. Chisq Change Prob Iter APBEFISK*BEFISK*NEME*TARSCSOP*VALLAS 128 9,373 1,0000 5 Step 1 The best model has generating class APBEFISK*BEFISK*NEME*TARSCSOP APBEFISK*BEFISK*NEME*VALLAS APBEFISK*BEFISK*TARSCSOP*VALLAS APBEFISK*NEME*TARSCSOP*VALLAS BEFISK*NEME*TARSCSOP*VALLAS Likelihood ratio chi square = 9,37253 DF = 128 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If Deleted Simple Effect is DF L.R. Chisq Change Prob Iter APBEFISK*BEFISK*NEME*TARSCSOP 32 22,984 ,8788 4 APBEFISK*BEFISK*NEME*VALLAS 64 21,262 1,0000 5 APBEFISK*BEFISK*TARSCSOP*VALLAS 128 7,580 1,0000 6 Step 2 The best model has generating class APBEFISK*BEFISK*NEME*TARSCSOP APBEFISK*BEFISK*NEME*VALLAS APBEFISK*NEME*TARSCSOP*VALLAS BEFISK*NEME*TARSCSOP*VALLAS Likelihood ratio chi square = 16,95204 DF = 256 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If Deleted Simple Effect is DF L.R. Chisq Change Prob Iter APBEFISK*BEFISK*NEME*TARSCSOP 32 24,300 ,8334 5 APBEFISK*BEFISK*NEME*VALLAS 64 24,673 1,0000 6 APBEFISK*NEME*TARSCSOP*VALLAS 32 11,773 ,9996 10 BEFISK*NEME*TARSCSOP*VALLAS 32 20,741 ,9372 7 Step 3 The best model has generating class APBEFISK*BEFISK*NEME*TARSCSOP APBEFISK*NEME*TARSCSOP*VALLAS BEFISK*NEME*TARSCSOP*VALLAS APBEFISK*BEFISK*VALLAS Likelihood ratio chi square = 41,62459 DF = 320 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If Deleted Simple Effect is DF L.R. Chisq Change Prob Iter APBEFISK*BEFISK*NEME*TARSCSOP 32 24,427 ,8285 5 APBEFISK*NEME*TARSCSOP*VALLAS 32 8,053 1,0000 14 BEFISK*NEME*TARSCSOP*VALLAS 32 19,355 ,9616 7 APBEFISK*BEFISK*VALLAS 64 37,067 ,9972 4 Step 4 The best model has generating class APBEFISK*BEFISK*NEME*TARSCSOP BEFISK*NEME*TARSCSOP*VALLAS APBEFISK*BEFISK*VALLAS APBEFISK*NEME*VALLAS APBEFISK*TARSCSOP*VALLAS Likelihood ratio chi square = 49,67729 DF = 352 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If Deleted Simple Effect is DF L.R. Chisq Change Prob Iter APBEFISK*BEFISK*NEME*TARSCSOP 32 28,924 ,6230 7 BEFISK*NEME*TARSCSOP*VALLAS 32 23,352 ,8669 7 APBEFISK*BEFISK*VALLAS 64 40,759 ,9896 10 APBEFISK*NEME*VALLAS 16 18,236 ,3103 13 APBEFISK*TARSCSOP*VALLAS 32 19,523 ,9591 5 Step 5 The best model has generating class APBEFISK*BEFISK*NEME*TARSCSOP BEFISK*NEME*TARSCSOP*VALLAS APBEFISK*NEME*VALLAS APBEFISK*TARSCSOP*VALLAS Likelihood ratio chi square = 90,43589 DF = 416 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If Deleted Simple Effect is DF L.R. Chisq Change Prob Iter APBEFISK*BEFISK*NEME*TARSCSOP 32 23,860 ,8494 6 BEFISK*NEME*TARSCSOP*VALLAS 32 20,584 ,9404 5 APBEFISK*NEME*VALLAS 16 14,476 ,5633 9 APBEFISK*TARSCSOP*VALLAS 32 23,881 ,8487 5 Step 6 The best model has generating class APBEFISK*BEFISK*NEME*TARSCSOP APBEFISK*NEME*VALLAS APBEFISK*TARSCSOP*VALLAS BEFISK*NEME*VALLAS BEFISK*TARSCSOP*VALLAS NEME*TARSCSOP*VALLAS Likelihood ratio chi square = 111,01966 DF = 448 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If Deleted Simple Effect is DF L.R. Chisq Change Prob Iter APBEFISK*BEFISK*NEME*TARSCSOP 32 18,838 ,9686 7 APBEFISK*NEME*VALLAS 16 14,244 ,5806 5 APBEFISK*TARSCSOP*VALLAS 32 18,706 ,9703 6 BEFISK*NEME*VALLAS 16 23,822 ,0935 5 BEFISK*TARSCSOP*VALLAS 32 24,159 ,8386 6 NEME*TARSCSOP*VALLAS 8 2,921 ,9392 5 Step 7 The best model has generating class APBEFISK*BEFISK*NEME*TARSCSOP APBEFISK*NEME*VALLAS BEFISK*NEME*VALLAS BEFISK*TARSCSOP*VALLAS NEME*TARSCSOP*VALLAS Likelihood ratio chi square = 129,72571 DF = 480 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If Deleted Simple Effect is DF L.R. Chisq Change Prob Iter APBEFISK*BEFISK*NEME*TARSCSOP 32 18,614 ,9714 6 APBEFISK*NEME*VALLAS 16 16,526 ,4169 5 BEFISK*NEME*VALLAS 16 23,358 ,1045 4 BEFISK*TARSCSOP*VALLAS 32 23,434 ,8642 6 NEME*TARSCSOP*VALLAS 8 5,733 ,6771 5 Step 8 The best model has generating class APBEFISK*NEME*VALLAS BEFISK*NEME*VALLAS BEFISK*TARSCSOP*VALLAS NEME*TARSCSOP*VALLAS APBEFISK*BEFISK*NEME APBEFISK*BEFISK*TARSCSOP APBEFISK*NEME*TARSCSOP BEFISK*NEME*TARSCSOP Likelihood ratio chi square = 148,34016 DF = 512 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If Deleted Simple Effect is DF L.R. Chisq Change Prob Iter APBEFISK*NEME*VALLAS 16 16,230 ,4371 5 BEFISK*NEME*VALLAS 16 23,284 ,1063 5 BEFISK*TARSCSOP*VALLAS 32 23,157 ,8733 6 NEME*TARSCSOP*VALLAS 8 5,332 ,7216 5 APBEFISK*BEFISK*NEME 16 25,565 ,0605 6 APBEFISK*BEFISK*TARSCSOP 32 26,908 ,7221 6 APBEFISK*NEME*TARSCSOP 8 9,288 ,3186 6 BEFISK*NEME*TARSCSOP 8 17,202 ,0281 6 Step 9 The best model has generating class APBEFISK*NEME*VALLAS BEFISK*NEME*VALLAS NEME*TARSCSOP*VALLAS APBEFISK*BEFISK*NEME APBEFISK*BEFISK*TARSCSOP APBEFISK*NEME*TARSCSOP BEFISK*NEME*TARSCSOP Likelihood ratio chi square = 171,49721 DF = 544 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If Deleted Simple Effect is DF L.R. Chisq Change Prob Iter APBEFISK*NEME*VALLAS 16 16,403 ,4252 6 BEFISK*NEME*VALLAS 16 21,397 ,1637 5 NEME*TARSCSOP*VALLAS 8 4,982 ,7596 6 APBEFISK*BEFISK*NEME 16 26,603 ,0461 6 APBEFISK*BEFISK*TARSCSOP 32 31,317 ,5010 7 APBEFISK*NEME*TARSCSOP 8 9,392 ,3103 6 BEFISK*NEME*TARSCSOP 8 16,688 ,0335 6 Step 10 The best model has generating class APBEFISK*NEME*VALLAS BEFISK*NEME*VALLAS APBEFISK*BEFISK*NEME APBEFISK*BEFISK*TARSCSOP APBEFISK*NEME*TARSCSOP BEFISK*NEME*TARSCSOP TARSCSOP*VALLAS Likelihood ratio chi square = 176,47871 DF = 552 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - * * * * * * * * * * * * * * * * * * * * * H I E R A R C H I C A L L O G L I N E A R * * * * * * * * * * * * * * * * * * * * * The final model has generating class APBEFISK*NEME*VALLAS BEFISK*NEME*VALLAS APBEFISK*BEFISK*NEME APBEFISK*BEFISK*TARSCSOP APBEFISK*NEME*TARSCSOP BEFISK*NEME*TARSCSOP TARSCSOP*VALLAS The Iterative Proportional Fit algorithm converged at iteration 0. The maximum difference between observed and fitted marginal totals is ,000 and the convergence criterion is ,250 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Goodness-of-fit test statistics Likelihood ratio chi square = 176,47871 DF = 552 P = 1,000 Pearson chi square = 164,10955 DF = 552 P = 1,000 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -