Regnerated results for the paper

python/logistic/logit_utils_gen.py

@@ -360,8 +360,8 @@ class LogisticPolyRegression:
             x: array of n floats
             y: array of n int in {0, 1}
         
-        Return:
-            pars
+        Return: 
+            dict {"pars", "cost", "success"}
     """
     def fit(self, x, y, pars0 = None, method = "local"):
         
@@ -391,7 +391,7 @@ class LogisticPolyRegression:
         
         else:
             assert False, "This method is not supported."
-        
+
         return {"pars": res.x, "cost": res.fun, "success": res.success}
 
     """
@@ -414,7 +414,8 @@ class LogisticPolyRegression:
             "LLF": log_likelihood, 
             "AIC": AIC, 
             "BIC": BIC, 
-            "A": classification accuracy (threshold values = 0.5 prob)}
+            "A": classification accuracy (threshold values = 0.5 prob),
+            "chi2": chi2 statistic,}
         
         Ref:
             https://en.wikipedia.org/wiki/Logistic_regression
@@ -514,6 +515,23 @@ class LogisticPolyRegression:
         return np.linalg.inv(H)
 
     """
+        Calculating standard errors fo model parameters for normal distribution of parameters:
+
+            pars ~ N(mean_pars, cov_pars)
+        
+        Input:
+            
+            cov_pars: array of rxr floats, variance-covariance matrix of parameters
+        
+        Return:
+            array of r floats, standard errors of parameters
+    """
+    def get_SE_pars_normal(self, cov_pars):
+        
+        # computing standard errors of parameters
+        return np.sqrt(np.diag(cov_pars))
+    
+    """
         Calculating quantiles of the model parameters at given probabilities p 
         for normal distribution of parameters: