SAS Enterprise Miner

User : richc
Date : 17MAR2006:14:11:52
Notes:

"EM Workspace" :

EM Workspace

RCLIB.FEVTEST

Input Data Settings:


  • All variables

  • Interval Variables

  • Class Variables

  • Notes: not available

    RCLIB.FEVVALID

    Input Data Settings:


  • All variables

  • Interval Variables

  • Class Variables

  • Notes: not available

    RCLIB.FEVTRAIN

    Input Data Settings:


  • All variables

  • Interval Variables

  • Class Variables

  • Notes: not available

    Tree

    Model assessment plot:

    SAS Graphics 

     
 Fit Statistic                     Training    Validation       Test 
  
 Average Squared Error                0.115        0.181       0.175 
 Sum of Squared Errors               37.739       29.430      28.693 
 Root Average Squared Error           0.340        0.425       0.418 
 Maximum Absolute Error               1.465        1.744       1.778 
 Divisor for ASE                    327.000      163.000     164.000 
 Total Degrees of Freedom           327.000         .           . 
 Number of Estimated Weights         21.000         .           . 
 Sum of Frequencies                 327.000      163.000     164.000 
 Sum Case Weights * Frequencies     327.000      163.000     164.000 
  
     
                                ROOT      V ROOT                  V 
 Node    Leaf     N    V N      ASE        ASE      AVERAGE    AVERAGE 
  
  16       1      8      1    0.26905    0.36250    1.17350    1.53600 
  46       2     18      9    0.15669    0.20362    1.61283    1.60700 
  47       3     11      7    0.16039    0.31497    1.74127    1.99086 
  48       4      6      3    0.27906    0.21901    1.35000    1.25900 
  49       5     15      6    0.15943    0.14152    1.60187    1.57267 
  18       6     14      6    0.22629    0.16563    1.86064    1.90667 
  19       7     41     15    0.24057    0.26233    2.00961    2.06847 
  10       8     14      6    0.27460    0.19525    2.29050    2.30633 
  22       9      5      5    0.12713    0.33406    2.35080    2.25340 
  54      10     10      6    0.36896    0.33446    2.41240    2.22117 
  55      11      8      3    0.23814    0.37123    2.55188    2.53833 
  56      12     11      3    0.36032    0.41647    2.52064    2.53000 
  57      13     18      6    0.30519    0.34265    2.71628    2.76933 
  12      14     36     21    0.35809    0.43504    2.77311    2.55352 
  26      15     24      8    0.38786    0.33687    2.90379    2.73363 
  27      16     32     15    0.35129    0.50789    3.15581    3.11173 
  68      17     17     10    0.52913    0.67576    3.63188    3.66690 
  69      18     18      9    0.40119    0.47408    4.01456    3.95389 
  45      19      7      9    0.35464    0.36938    4.39686    4.48700 
  29      20      8     11    0.61702    0.41324    3.18913    3.18727 
  15      21      6      4    0.66859    1.14315    4.82617    3.91025
  • English rules

  • Sequence

  • Matrix

    Target information
    Name: FEV
    Label: FEV
    Measurement: interval

    Tree settings

    No profile information defined
    Splitting criterion: Variance Reduction
    Minimum number of observations in a leaf: 5
    Observations required for a split search: 10
    Maximum number of branches from a node: 2
    Maximum depth of tree: 6
    Splitting rules saved in each node: 4
    Surrogate rules saved in each node: 3
    Do not treat missing as an acceptable value
    Model assessment measure: Average Square Error
    Subtree: Best assessment value
    Observations sufficient for split search: 328
    Maximum tries in an exhaustive split search: 5000

  • Log

  • Score Code
    Model assessment settings
    Train data set is not selected for assessment.
    Validation data set is selected for assessment.
    Test data set is not selected for assessment.
    Scored data set: 5000 observations are saved for interactive model assessment.
    Note: no confusion matrix is available due to a cause such as an extreme rare target event.

  • Notes: not available

    End Report

    Path Information


    Name: Tree_T3BG_I70
    Target: FEV
    Description:
    Mining Function: Transform
    Subject: No subject
    Rating: 0

  • Metadata Information

  • Input Variables Required for Scoring

  • Output Variables Produced by Scoring

  • Target Variables

  • Datastep Score Code

  • C Score Code