GLM Example: Step ('true') with StepTable - Teradata Vantage

Input

• InputTable: admissions_train, as in GLM Example: Logistic Regression Analysis with Intercept

SQL Call

SELECT * FROM GLM (
  ON admissions_train AS InputTable
  OUT TABLE OutputTable (glm_admissions_model)
  OUT TABLE StepTable (glm_admissions_model_step)
  USING
  TargetColumns ('admitted', 'masters', 'gpa', 'stats', 'programming')
  CategoricalColumns ('masters', 'stats', 'programming')
  Family ('LOGISTIC')
  LinkFunction ('LOGIT')
  WeightColumn ('1')
  StopThreshold (0.01)
  MaxIterNum (25)
  Step ('t')
  Intercept ('true')
) AS dt;

Onscreen Output

 predictor               estimate             std_error          z_score              p_value              significance                           

 ----------------------- -------------------- ------------------ -------------------- -------------------- ---------------------------------------

 (Intercept)             -0.09531019628047943 0.4369310140609741 -0.21813499927520752   0.8273239731788635                                       

 masters.no                2.1747500896453857 0.8679909706115723    2.505500078201294 0.012227799743413925 *                                     

 ITERATIONS #                             4.0                0.0                  0.0                  0.0 Number of Fisher Scoring iterations   

 ROWS #                                  39.0                0.0                  0.0                  0.0 Number of rows                        

 Residual deviance          41.62260055541992                0.0                  0.0                  0.0 on 37 degrees of freedom              

 Pearson goodness of fit                 39.0                0.0                  0.0                  0.0 on 37 degrees of freedom              

 AIC                        45.62260055541992                0.0                  0.0                  0.0 Akaike information criterion          

 BIC                        48.94972229003906                0.0                  0.0                  0.0 Bayesian information criterion        

 Wald Test                  7.734839916229248                0.0                  0.0 0.020912254229187965 *                                     

 Dispersion parameter                     1.0                0.0                  0.0                  0.0 Taken to be 1 for BINOMIAL and POISSON.

OutputTable: glm_admissions_model

 attribute predictor   category estimate             std_err            z_score              p_value              significance family  

 --------- ----------- -------- -------------------- ------------------ -------------------- -------------------- ------------ --------

         0 (Intercept) NULL     -0.09531019628047943 0.4369310140609741 -0.21813499927520752   0.8273239731788635              LOGISTIC

         1 masters     yes                      NULL               NULL                 NULL                 NULL NULL         LOGISTIC

        -1 Loglik      NULL       -20.81130027770996               39.0                  0.0                  0.0 NULL         LOGISTIC

         2 masters     no         2.1747500896453857 0.8679909706115723    2.505500078201294 0.012227799743413925 *            LOGISTIC

StepTable: glm_admissions_model_step

 attribute predictor   category estimate             std_err            z_score              p_value              significance family  

 --------- ----------- -------- -------------------- ------------------ -------------------- -------------------- ------------ --------

         0 (Intercept) NULL     -0.09531019628047943 0.4369310140609741 -0.21813499927520752   0.8273239731788635              LOGISTIC

         1 masters     yes                      NULL               NULL                 NULL                 NULL NULL         LOGISTIC

        -1 Loglik      NULL       -20.81130027770996               39.0                  0.0                  0.0 NULL         LOGISTIC

         2 masters     no         2.1747500896453857 0.8679909706115723    2.505500078201294 0.012227799743413925 *            LOGISTIC