The arboretum procedure

Partial Listing of R-Squares for Target Variable

This section of the output ranks all model effects by their R-square values. The degrees of freedom (DF) associated with

each effect is also listed. Effects that have an R-square value less than the MINR2 = cutoff value are not chosen for the

model. These effects are labeled as "R2 < MINR2" in the table. The remaining significant variables are analyzed in a

subsequent forward selection regression.

There are four types of model effects:

Class effects are estimated for each class variable and all possible two-factor interactions. The R-square statistic is

calculated for each class effect using a one-way analysis of variance. Two-factor interaction effects are

constructed by combining all possible levels of each class variable into one term. Because the NOINTER option

was specified, the two-factor interactions are not used in the final forward stepwise regression. The degrees of

freedom for a class effect is equal to: (the number of unique factor levels minus 1). For two-factor interactions, the

degrees of freedom is equal to: (the number of levels in factor A multiplied by the number of levels in factor B

minus 1).

q   

Group effects are created by reducing each class effect through an analysis of means. The degrees of freedom for

each group effect is equal to the number of levels.

q   

VAR effects are estimated from interval variables as standard regression inputs. A simple linear regression is

performed to determine the R2 statistic for interval inputs. The degrees of freedom is always equal to 1.

q   

AOV16 effects are calculated as a result of grouping numeric variables into a maximum of 16 equally spaced

buckets. AOV16 effects may account for possible non-linearity in the target variable AMOUNT. The degrees of

freedom are calculated as the number of groups. Because the NOAOV16 option was specified, the AOV16

variables are not used in the final forward stepwise regression.

q   

Note that the original input LEISURE has the largest R-square statistic with the target. Several AOV16 and group

variables have large R-square values, but these effects are not used in the final forward stepwise regression.

 

                    DMINE: Continuous Target

                  R-Squares for Target variable: AMOUNT

       Effect                                   DF          R2 

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

       Var:   LEISURE                            1      0.4827

       AOV16: APPAREL                           12      0.4762

       Class: KITCHEN*STA                        8      0.4268

       Group: KITCHEN*STATECOD                   9      0.4210

       Class: KITCHEN*LUXURY                    16      0.4019

       Var:   APPAREL                            1      0.4001

       Group: KITCHEN*LUXURY                     5      0.3959

       AOV16: DOMESTIC                          15      0.3869

       Var:   DOMESTIC                           1      0.3652

       AOV16: FREQUENT                          11      0.3418

       Class: LUXURY*STATECOD                  101      0.3335

       Group: LUXURY*STATECOD                    6      0.3284

       Class: LUXURY*TMKTORD                     7      0.3212

       Group: LUXURY*TMKTORD                     4      0.3177

       Class: KITCHEN*DISHES                    42      0.3128

       Class: MARITAL*KITCHEN                   17      0.3084

       Group: KITCHEN*DISHES                     5      0.3066

       Var:   FREQUENT                           1      0.3048

       Class: TMKTORD*STATECOD                 110      0.3046

       Group: MARITAL*KITCHEN                    5      0.3033

---

       Group: TMKTORD*STATECOD                   8      0.2995

       Class: KITCHEN*TMKTORD                   26      0.2921

             

 

       Group: KITCHEN*TMKTORD                    5      0.2870

       AOV16: DPM12                             12      0.2770

       Class: NTITLE*KITCHEN                    28      0.2717

       Group: NTITLE*KITCHEN                     6      0.2690

       Class: KITCHEN*RACE                      25      0.2594

       Class: KITCHEN*EDLEVEL                   26      0.2572

       Group: KITCHEN*RACE                       5      0.2568

       Class: LUXURY*DISHES                     15      0.2547

       Group: KITCHEN*EDLEVEL                    6      0.2533

       Group: LUXURY*DISHES                      3      0.2504

       Class: LUXURY*RACE                        8      0.2455

       Group: LUXURY*RACE                        2      0.2447

       Class: KITCHEN*ORIGIN                    35      0.2438

       Class: LUXURY*ORIGIN                     11      0.2419

       Class: NTITLE*LUXURY                      7      0.2419

       Group: KITCHEN*ORIGIN                     6      0.2407

       Group: NTITLE*LUXURY                      2      0.2406

       Class: LUXURY*NUMCARS                     6      0.2394

       Class: APRTMNT*LUXURY                     3      0.2389

       Class: TELIND*LUXURY                      3      0.2386

       Class: LUXURY*EDLEVEL                     7      0.2384

       Additional effects are not listed

 

                R-Squares for Target variable: AMOUNT  

       Group: DISHES*NUMCARS                     7      0.0288

       Class: SNGLMOM*DISHES                    13      0.0283

       Group: SNGLMOM*DISHES                     5      0.0279

       Class: DISHES                             9      0.0271

       Group: DISHES                             4      0.0268

       Var:   COATS                              1      0.0228

       AOV16: FLATWARE                          10      0.0221

       Var:   FLATWARE                           1      0.0196    R2 < MINR2

       AOV16: RETURN                             2      0.0195    R2 < MINR2

       Class: NTITLE*RACE                       17      0.0148    R2 < MINR2

       Group: NTITLE*RACE                        6      0.0146    R2 < MINR2

       Var:   RETURN                             1      0.0146    R2 < MINR2

       AOV16: WCOAT                             10      0.0122    R2 < MINR2

       Class: ORIGIN*EDLEVEL                    21      0.0118    R2 < MINR2

       Class: RACE*EDLEVEL                      14      0.0116    R2 < MINR2

       Group: ORIGIN*EDLEVEL                     8      0.0116    R2 < MINR2

       Group: RACE*EDLEVEL                       5      0.0114    R2 < MINR2

       Var:   WCOAT                              1      0.0107    R2 < MINR2

       AOV16: CUSTDATE                          15      0.0106    R2 < MINR2

       Class: RACE*HEAT                         14      0.0103    R2 < MINR2

       Group: RACE*HEAT                          5      0.0102    R2 < MINR2

       Class: ORIGIN*HEAT                       22      0.0093    R2 < MINR2

---