--> READ;NOBS=630 ;NVAR=2 ; file = mma14p1binary.asc ; NAMES=CHARTER, LNRELP $ --> PROBIT;Lhs=charter;Rhs=ONE,lnrelp$ Normal exit from iterations. Exit status=0. +---------------------------------------------+ | Binomial Probit Model | | Maximum Likelihood Estimates | | Model estimated: Nov 09, 2004 at 03:30:45PM.| | Dependent variable CHARTER | | Weighting variable None | | Number of observations 630 | | Iterations completed 6 | | Log likelihood function -204.4109 | | Restricted log likelihood -375.0617 | | Chi squared 341.3016 | | Degrees of freedom 1 | | Prob[ChiSqd > value] = .0000000 | | Hosmer-Lemeshow chi-squared = 18.96258 | | P-value= .00423 with deg.fr. = 6 | +---------------------------------------------+ +---------+--------------+----------------+--------+---------+----------+ |Variable | Coefficient | Standard Error |b/St.Er.|P[|Z|>z] | Mean of X| +---------+--------------+----------------+--------+---------+----------+ Index function for probability Constant 1.194360403 .89508361E-01 13.344 .0000 LNRELP -1.055514516 .76115584E-01 -13.867 .0000 .27455808 (Note: E+nn or E-nn means multiply by 10 to + or -nn power.) +----------------------------------------+ | Fit Measures for Binomial Choice Model | | Probit model for variable CHARTER | +----------------------------------------+ | Proportions P0= .282540 P1= .717460 | | N = 630 N0= 178 N1= 452 | | LogL = -204.41086 LogL0 = -375.0617 | | Estrella = 1-(L/L0)^(-2L0/n) = .51455 | +----------------------------------------+ | Efron | McFadden | Ben./Lerman | | .47845 | .45499 | .79475 | | Cramer | Veall/Zim. | Rsqrd_ML | | .49082 | .64650 | .41827 | +----------------------------------------+ | Information Akaike I.C. Schwarz I.C. | | Criteria .65527 421.71317 | +----------------------------------------+ Frequencies of actual & predicted outcomes Predicted outcome has maximum probability. Threshold value for predicting Y=1 = .5000 Predicted ------ ---------- + ----- Actual 0 1 | Total ------ ---------- + ----- 0 117 61 | 178 1 38 414 | 452 ------ ---------- + ----- Total 155 475 | 630 --> LOGIT; Lhs=charter;Rhs=ONE,lnrelp$ Normal exit from iterations. Exit status=0. +---------------------------------------------+ | Multinomial Logit Model | | Maximum Likelihood Estimates | | Model estimated: Nov 09, 2004 at 03:30:47PM.| | Dependent variable CHARTER | | Weighting variable None | | Number of observations 630 | | Iterations completed 7 | | Log likelihood function -206.8270 | | Restricted log likelihood -375.0617 | | Chi squared 336.4694 | | Degrees of freedom 1 | | Prob[ChiSqd > value] = .0000000 | | Hosmer-Lemeshow chi-squared = 23.33705 | | P-value= .00149 with deg.fr. = 7 | +---------------------------------------------+ +---------+--------------+----------------+--------+---------+----------+ |Variable | Coefficient | Standard Error |b/St.Er.|P[|Z|>z] | Mean of X| +---------+--------------+----------------+--------+---------+----------+ Characteristics in numerator of Prob[Y = 1] Constant 2.053124899 .16893068 12.154 .0000 LNRELP -1.822530412 .14456807 -12.607 .0000 .27455808 +--------------------------------------------------------------------+ | Information Statistics for Discrete Choice Model. | | M=Model MC=Constants Only M0=No Model | | Criterion F (log L) -206.82697 -375.06167 -436.68272 | | LR Statistic vs. MC 336.46940 .00000 .00000 | | Degrees of Freedom 1.00000 .00000 .00000 | | Prob. Value for LR .00000 .00000 .00000 | | Entropy for probs. 206.82697 375.06167 436.68272 | | Normalized Entropy .47363 .85889 1.00000 | | Entropy Ratio Stat. 459.71151 123.24211 .00000 | | Bayes Info Criterion 420.09966 756.56906 879.81117 | | BIC - BIC(no model) 459.71151 123.24211 .00000 | | Pseudo R-squared .44855 .00000 .00000 | | Pct. Correct Prec. 84.44444 .00000 50.00000 | | Means: y=0 y=1 y=2 y=3 yu=4 y=5, y=6 y>=7 | | Outcome .2825 .7175 .0000 .0000 .0000 .0000 .0000 .0000 | | Pred.Pr .2825 .7175 .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 CHARTER | +----------------------------------------+ | Proportions P0= .282540 P1= .717460 | | N = 630 N0= 178 N1= 452 | | LogL = -206.82697 LogL0 = -375.0617 | | Estrella = 1-(L/L0)^(-2L0/n) = .50771 | +----------------------------------------+ | Efron | McFadden | Ben./Lerman | | .47526 | .44855 | .79271 | | Cramer | Veall/Zim. | Rsqrd_ML | | .48871 | .64053 | .41379 | +----------------------------------------+ | Information Akaike I.C. Schwarz I.C. | | Criteria .66294 426.54538 | +----------------------------------------+ Frequencies of actual & predicted outcomes Predicted outcome has maximum probability. Threshold value for predicting Y=1 = .5000 Predicted ------ ---------- + ----- Actual 0 1 | Total ------ ---------- + ----- 0 118 60 | 178 1 38 414 | 452 ------ ---------- + ----- Total 156 474 | 630 --> MSCORE ; Lhs = charter ; Rhs = ONE,lnrelp;Nbt = 50$ +----------------------------------------------------------------------+ | Maximum Score Estimates of Linear Quantile | | Regression Model from Binary Response Data | | Quantile .500 Number of Parameters = 2 | | Observations input = 630 Maximum Iterations = 500 | | End Game Iterations = 1 Bootstrap Estimates = 50 | | Check Ties? No | | Save bootstraps? No | | Start values from MSCORE (normalized) | | Normal exit after 1 iterations. | | Score functions: Naive At theta(0) Maximum | | Raw .43492 .66984 .73333 | | Normalized .71746 .83492 .86667 | | Estimated MSEs from 50 bootstrap samples | | (Nonconvergence in 0 cases) | | Angular deviation (radians) of bootstraps from estimate | | Mean square = .159391 Mean absolute = .105079 | | Standard errors below are based on bootstrap mean squared | | deviations. These and the t-ratios are only approximations. | +----------------------------------------------------------------------+ +---------+--------------+----------------+--------+---------+----------+ |Variable | Coefficient | Standard Error |b/St.Er.|P[|Z|>z] | Mean of X| +---------+--------------+----------------+--------+---------+----------+ Constant .7756081999 .12013620 6.456 .0000 LNRELP -.6312146388 .10303600 -6.126 .0000 .27455808 Frequencies of actual & predicted outcomes Predicted outcome is the sign of x(i)*theta. Predicted ------ ---------- + ----- Actual 0 1 | Total ------ ---------- + ----- 0 115 63 | 178 1 31 421 | 452 ------ ---------- + ----- Total 146 484 | 630