7/28/2019 Modelo Logit Dapr
1/3
MODELO LOGIT DAPR
--> CREATE;PRECR=(10-PREC)/PREC$--> CALC;COEF1=B(1)$-->
CALC;COEF2=B(2)$--> CALC;COEF3=B(3)$-->
CALC;COEF4=B(4)$--> CALC;COEF5=B(5)$-->
CALC;COEF6=B(6)$--> CALC;COEF7=B(7)$-->
CALC;COEF8=B(8)$--> CALC;COEF9=B(9)$-->
CALC;COEF10=B(10)$-->
CREATE;EXPO=EXP(-(COEF1+COEF2*ING+COEF3*EDU+COEF4*CONT+COEF5*DIST+COEF6*E...-->
CREATE;DAPR=10/(1+EXPO)$--> DSTAT;RHS=DAPR$-->
LIST;DAPR$--> ENDPROC-->
LOGIT;Lhs=PSI;Rhs=ONE,ING,EDU,CONT,DIST,ENF,GEN,HIJO,EDAD,PRECR$Normal
exit from iterations. Exit
status=0.+---------------------------------------------+|
Multinomial Logit Model || Maximum Likelihood Estimates || Model
estimated: May 25, 2013 at 00:22:46PM.|| Dependent variable PSI
|
| Weighting variable None || Number of observations 390 ||
Iterations completed 6 || Log likelihood function -208.9167 ||
Restricted log likelihood -266.2930 || Chi squared 114.7524 ||
Degrees of freedom 9 || Prob[ChiSqd > value] = .0000000 ||
Hosmer-Lemeshow chi-squared = 30.90944 || P-value= .00015 with
deg.fr. = 8
|+---------------------------------------------++---------+--------------+----------------+--------+---------+----------+|Variable
| Coefficient | Standard Error |b/St.Er.|P[|Z|>z] | Mean of
X|+---------+--------------+----------------+--------+---------+----------+
Characteristics in numerator of Prob[Y = 1]Constant -.76942087
1.18210514 -.651 .5151
ING .46050491 .09895540 4.654 .0000 3.34871795EDU .48156827
.15502677 3.106 .0019 3.13846154CONT .73673482 .26816945 2.747
.0060 .42820513DIST -.63778590 .24870072 -2.564 .0103 3.77179487ENF
.27756931 .28662595 .968 .3328 .24871795GEN -.07058832 .25199488
-.280 .7794 .50769231HIJO -.00140102 .26420406 -.005 .9958
.67948718EDAD -.15117526 .10485794 -1.442 .1494 2.67435897PRECR
.16360636 .03975684 4.115 .0000 3.68411033
+--------------------------------------------------------------------+|
Information Statistics for Discrete Choice Model. || M=Model
MC=Constants Only M0=No Model || Criterion F (log L) -208.91674
-266.29296 -270.32740 || LR Statistic vs. MC 114.75243 .00000
.00000 || Degrees of Freedom 9.00000 .00000 .00000 || Prob. Value
for LR .00000 .00000 .00000 || Entropy for probs. 208.91674
266.29296 270.32740 |
| Normalized Entropy .77283 .98508 1.00000 || Entropy Ratio
Stat. 122.82131 8.06889 .00000 || Bayes Info Criterion 471.52881
586.28123 594.35012 || BIC - BIC(no model) 122.82131 8.06889 .00000
|| Pseudo R-squared .21546 .00000 .00000 || Pct. Correct Prec.
75.64103 .00000 50.00000 || Means: y=0 y=1 y=2 y=3 yu=4 y=5, y=6
y>=7 || Outcome .4282 .5718 .0000 .0000 .0000 .0000 .0000 .0000
|| Pred.Pr .4282 .5718 .0000 .0000 .0000 .0000 .0000 .0000 ||
Notes: Entropy computed as Sum(i)Sum(j)Pfit(i,j)*logPfit(i,j). ||
Normalized entropy is computed against M0. || Entropy ratio
statistic is computed against M0. || BIC = 2*criterion -
log(N)*degrees of freedom. || If the model has only constants or if
it has no constants, || the statistics reported here are not
useable.
|+--------------------------------------------------------------------+
+----------------------------------------+| Fit Measures for
Binomial Choice Model || Logit model for variable PSI |
7/28/2019 Modelo Logit Dapr
2/3
+----------------------------------------+| Proportions P0=
.428205 P1= .571795 || N = 390 N0= 167 N1= 223 || LogL = -208.91674
LogL0 = -266.2930 || Estrella = 1-(L/L0)^(-2L0/n) = .28207
|+----------------------------------------+| Efron | McFadden |
Ben./Lerman || .28061 | .21546 | .64354 |
| Cramer | Veall/Zim. | Rsqrd_ML || .27208 | .39382 | .25490
|+----------------------------------------+| Information Akaike
I.C. Schwarz I.C. || Criteria 1.12265 477.49495
|+----------------------------------------+Frequencies of actual
& predicted outcomesPredicted outcome has maximum
probability.Threshold value for predicting Y=1 = .5000
Predicted------ ---------- + -----Actual 0 1 | Total------
---------- + -----0 113 54 | 1671 41 182 | 223
------ ---------- + -----
Total 154 236 |
390=======================================================================Analysis
of Binary Choice Model Predictions Based on Threshold =
.5000-----------------------------------------------------------------------Prediction
Success-----------------------------------------------------------------------Sensitivity
= actual 1s correctly predicted 81.614%Specificity = actual 0s
correctly predicted 67.665%Positive predictive value = predicted 1s
that were actual 1s 77.119%Negative predictive value = predicted 0s
that were actual 0s 73.377%Correct prediction = actual 1s and 0s
correctly predicted
75.641%-----------------------------------------------------------------------Prediction
Failure-----------------------------------------------------------------------False
pos. for true neg. = actual 0s predicted as 1s 32.335%False neg.
for true pos. = actual 1s predicted as 0s 18.386%False pos. for
predicted pos. = predicted 1s actual 0s 22.881%
False neg. for predicted neg. = predicted 0s actual 1s
26.623%False predictions = actual 1s and 0s incorrectly predicted
24.359%=======================================================================-->
PROC = DAPR$--> ENDPROC$-->
CREATE;PRECR=(10-PREC)/PREC$--> CALC;COEF1=B(1)$-->
CALC;COEF2=B(2)$--> CALC;COEF3=B(3)$-->
CALC;COEF4=B(4)$--> CALC;COEF5=B(5)$-->
CALC;COEF6=B(6)$--> CALC;COEF7=B(7)$-->
CALC;COEF8=B(8)$--> CALC;COEF9=B(9)$-->
CALC;COEF10=B(10)$
-->
CREATE;EXPO=EXP(-(COEF1+COEF2*ING+COEF3*EDU+COEF4*CONT+COEF5*DIST+COEF6*E...-->
CREATE;DAPR=10/(1+EXPO)$--> DSTAT;RHS=DAPR$Descriptive
StatisticsAll results based on nonmissing
observations.===============================================================================Variable
Mean Std.Dev. Minimum Maximum
Cases===============================================================================-------------------------------------------------------------------------------All
observations in current
sample-------------------------------------------------------------------------------DAPR
5.71794872 2.54349337 .471378667 9.92352956 390
