Bayesian Logistic Regression Models for Credit Scoring by Gregg Webster

 
 
D2: R output for Bayesian logistic regression model on “new” data with non-
informative prior 
Iterations = 500001:510000 
Thinning interval = 1
Number of chains = 1
Sample size per chain = 10000
1. Empirical mean and standard deviation for each variable, 
plus standard error of the mean: 
Mean SD Naive SE Time-series SE 
(Intercept) -9.212e+00 1.538e+00 1.538e-02 1.258e-01 
LOAN 5.248e-06 1.398e-05 1.398e-07 1.135e-06 
MORTDUE -7.716e-06 6.984e-06 6.984e-08 5.136e-07 
VALUE 2.173e-06 5.727e-06 5.727e-08 4.358e-07 
REASONHomeImp 9.077e-02 3.562e-01 3.562e-03 2.747e-02 
JOBOffice -9.888e-01 5.947e-01 5.947e-03 4.724e-02 
JOBOther 1.646e-01 4.717e-01 4.717e-03 3.383e-02 
JOBProfExe 1.176e-01 5.555e-01 5.555e-03 3.766e-02 
JOBSales 3.568e+00 9.672e-01 9.672e-03 7.448e-02 
JOBSelf -2.271e-01 9.678e-01 9.678e-03 8.455e-02 
YOJ -2.852e-02 2.233e-02 2.233e-04 1.652e-03 
DEROG 7.688e-01 2.209e-01 2.209e-03 1.639e-02 
DELINQ 1.236e+00 1.742e-01 1.742e-03 1.204e-02 

---

125 
CLAGE -7.204e-03 2.083e-03 2.083e-05 1.461e-04 
NINQ 2.123e-01 7.219e-02 7.219e-04 5.723e-03 
CLNO -4.485e-02 1.744e-02 1.744e-04 1.458e-03 
DEBTINC 2.515e-01 3.642e-02 3.642e-04 3.043e-03 
2. Quantiles for each variable: 
2.5% 25% 50% 75% 97.5% 
(Intercept) -1.241e+01 -1.022e+01 -9.093e+00 -8.134e+00 -6.470e+00 
LOAN -2.320e-05 -4.472e-06 5.762e-06 1.545e-05 3.118e-05 
MORTDUE -2.196e-05 -1.203e-05 -7.241e-06 -2.907e-06 5.288e-06 
VALUE -9.056e-06 -1.559e-06 2.280e-06 5.789e-06 1.395e-05 
REASONHomeImp -5.866e-01 -1.532e-01 9.478e-02 3.365e-01 7.699e-01 
JOBOffice -2.101e+00 -1.392e+00 -9.925e-01 -5.842e-01 1.343e-01 
JOBOther -7.109e-01 -1.476e-01 1.516e-01 4.850e-01 1.116e+00 
JOBProfExe -9.444e-01 -2.559e-01 1.032e-01 4.617e-01 1.279e+00 
JOBSales 1.643e+00 2.937e+00 3.529e+00 4.213e+00 5.488e+00 
JOBSelf -2.182e+00 -8.519e-01 -1.890e-01 4.236e-01 1.624e+00 
YOJ -7.150e-02 -4.308e-02 -2.810e-02 -1.333e-02 1.415e-02 
DEROG 3.742e-01 6.119e-01 7.583e-01 9.061e-01 1.271e+00 
DELINQ 8.960e-01 1.116e+00 1.239e+00 1.349e+00 1.581e+00 
CLAGE -1.112e-02 -8.553e-03 -7.233e-03 -5.860e-03 -3.071e-03 
NINQ 6.882e-02 1.633e-01 2.130e-01 2.609e-01 3.505e-01 
CLNO -7.773e-02 -5.703e-02 -4.547e-02 -3.242e-02 -1.056e-02 
DEBTINC 1.894e-01 2.248e-01 2.482e-01 2.748e-01 3.295e-01 

---

126 

---

127 

---

128