SAS ƒVƒXƒeƒ€

The ADAPTIVEREG Procedure

Model Information
Data Set WORK.AUTOMPG
Response Variable MPG
Class Variables Cylinders Year Origin
Distribution Normal
Link Function Identity

Fit Controls
Maximum Number of Bases 21
Maximum Order of Interaction 1
Degrees of Freedom per Knot 2
Knot Separation Parameter 0.05
Penalty for Variable Reentry 0
Missing Value Handling Include

Class Level Information
Class Levels Values
Cylinders 5 3 4 5 6 8
Year 13 70 71 72 73 74 75 76 77 78 79 80 81 82
Origin 3 1 2 3

Number of Observations Read 398
Number of Observations Used 398

Fit Statistics
GCV 11.55804
GCV R-Square 0.81128
Effective Degrees of Freedom 23
R-Square 0.83161
Adjusted R-Square 0.82682
Mean Square Error 10.57977
Average Square Error 10.26079

Regression Spline Model after Backward Selection
Name Coefficient Parent Variable Knot Levels
Basis0 29.4394   Intercept    
Basis2 0.004412 Basis0 Weight 3139.00  
Basis3 -21.2899 Basis0 Horsepower .  
Basis6 0.1534 Basis3 Horsepower 158.00  
Basis7 2.3920 Basis3 Year   10 12 11 9 8 7 3
Basis9 1.6658 Basis0 Acceleration 21.0000  
Basis10 0.4672 Basis0 Acceleration 21.0000  
Basis11 -8.1766 Basis0 Cylinders   0 3
Basis13 -10.0976 Basis4 Origin   0
Basis15 2.1354 Basis0 Origin   2
Basis17 6.7675 Basis0 Cylinders   3
Basis19 1.4987 Basis0 Year   3 10 12 11 9

ANOVA Decomposition
Functional
Component
Number of
Bases
DF Change If Omitted
Lack of Fit GCV
Weight 1 2 299.55 0.7165
Horsepower 1 2 1324.81 3.5875
Year 2 4 1183.22 3.0358
Acceleration 2 4 287.76 0.5546
Cylinders 2 4 321.11 0.6470
Origin 2 4 316.04 0.6330

Variable Importance
Variable Number of
Bases
Importance
Horsepower 1 100.00
Year 2 85.46
Weight 1 21.10
Cylinders 2 19.08
Origin 2 18.67
Acceleration 2 16.38

Panel of fit diagnostics for MPG with GCV parameter 11.558. This plot consists of two side-by-side plots that show the spread in the fitted values about their mean and the spread in the residuals respectively.

Panel of component plots

Selection plot for MPG after backward selection