Title 'Multiple Collinearity Example'.
Data list fixed records=1
	/1 gpa 1-3 greq 5-7 grev 9-11 mat 13-14 ar 16-18.
begin data
3.2 625 540 65 2.7
4.1 575 680 75 4.5
3.0 520 480 65 2.5
2.6 545 520 55 3.1
3.7 520 490 75 3.6
4.0 655 535 65 4.3
4.3 630 720 75 4.6
2.7 500 500 75 3.0
3.6 605 575 65 4.7
4.1 555 690 75 3.4
2.7 505 545 55 3.7
2.9 540 515 55 2.6
2.5 520 520 55 3.1
3.0 585 710 65 2.7
3.3 600 610 85 5.0
3.2 625 540 65 2.7
4.1 575 680 75 4.5
3.0 520 480 65 2.5
2.6 545 520 55 3.1
3.7 520 490 75 3.6
4.0 655 535 65 4.3
4.3 630 720 75 4.6
2.7 500 500 75 3.0
3.6 605 575 65 4.7
4.1 555 690 75 3.4
2.7 505 545 55 3.7
2.9 540 515 55 2.6
2.5 520 520 55 3.1
3.0 585 710 65 2.7
3.3 600 610 85 5.0
end data.

compute new=greq+grev+mat+(.5*normal(1)).
execute.

Regression variables=gpa,greq,grev,mat,ar,new 
	/descriptives=mean,stddev,corr,n
	/statistics=r,anova,cha,coeff,ci,collin,tol
	/criteria=tolerance (0.00000001)
	/dependent=gpa 
	/method=enter.

Regression variables=gpa,greq,grev,mat,ar
        /descriptives=mean,stddev,corr,n
        /statistics=r,anova,cha,coeff,ci,collin,tol,history
        /dependent=gpa
	/method=enter.







OUTPUT:



22 Dec 99   SPSS for Unix, Release 6.1 (AIX 3.2)                                                                              Page 1
17:49:22    UCLA OAC                       IBM RS6000       AIX 3.2.5/4.


For AIX 3.2.5/4.        UCLA OAC                                 SPSS ID 90095



                                     * * * *   M U L T I P L E   R E G R E S S I O N   * * * *


Listwise Deletion of Missing Data

              Mean  Std Dev  Label

GPA          3.313     .600
GREQ       565.333   48.618
GREV       575.333   83.034
MAT         67.000    9.248
AR           3.567     .838
NEW       1207.569  118.205

N of Cases =    30

Correlation:

                GPA       GREQ       GREV        MAT         AR        NEW

GPA           1.000       .611       .581       .604       .621       .705
GREQ           .611      1.000       .468       .267       .508       .759
GREV           .581       .468      1.000       .426       .405       .927
MAT            .604       .267       .426      1.000       .525       .486
AR             .621       .508       .405       .525      1.000       .534
NEW            .705       .759       .927       .486       .534      1.000


22 Dec 99   Multiple Collinearity Example                                                                                     Page 3
17:49:22    UCLA OAC                       IBM RS6000       AIX 3.2.5/4.


                                     * * * *   M U L T I P L E   R E G R E S S I O N   * * * *

Equation Number 1    Dependent Variable..   GPA

  Descriptive Statistics are printed on Page    2

Block Number  1.  Method:  Enter

*  *  *  *  *  *  *  ***  WARNING  ***  *  *  *  *  *  *  *

The following variables in the equation have low tolerances:
         Variable    Tolerance
          NEW                .00001
          GREQ               .00007
          GREV               .00002

*  *  *  *  *  * ***  END OF WARNING  ***  *  *  *  *  *  *


Variable(s) Entered on Step Number  1..    NEW
                                    2..    MAT
                                    3..    AR
                                    4..    GREQ
                                    5..    GREV


Multiple R           .81323                                             Analysis of Variance
R Square             .66134          R Square Change    .66134                              DF      Sum of Squares      Mean Square
Adjusted R Square    .59078          F Change          9.37336          Regression           5             6.90083          1.38017
Standard Error       .38372          Signif F Change    .0000           Residual            24             3.53384           .14724

                                                                        F =       9.37336       Signif F =  .0000


------------------------------------------ Variables in the Equation ------------------------------------------

Variable              B        SE B     95% Confdnce Intrvl B       Beta  Tolerance        VIF         T  Sig T

GREQ            .213276     .172125     -.141972      .568524  17.286077  7.250E-05  13792.328     1.239  .2273
GREV            .212093     .173180     -.145333      .569519  29.359129  2.455E-05  40726.224     1.225  .2326
MAT             .230845     .172926     -.126057      .587748   3.558834    .001985    503.661     1.335  .1944
AR              .150697     .112061     -.080587      .381980    .210638    .575146      1.739     1.345  .1913
NEW            -.210503     .173122     -.567810      .146804 -41.481229  1.212E-05  82477.926    -1.216  .2358
(Constant)    -1.090440    1.081968    -3.323512     1.142633                                     -1.008  .3236

22 Dec 99   Multiple Collinearity Example                                                                                     Page 4
17:49:22    UCLA OAC                       IBM RS6000       AIX 3.2.5/4.

Collinearity Diagnostics

Number  Eigenval     Cond  Variance Proportions
                    Index  Constant     GREQ     GREV      MAT       AR      NEW
    1    5.94278    1.000    .00012   .00000   .00000   .00000   .00080   .00000
    2     .03196   13.636    .01496   .00000   .00000   .00000   .71599   .00000
    3     .01200   22.257    .04506   .00000   .00002   .00107   .01000   .00000
    4     .01038   23.930    .06158   .00001   .00001   .00153   .07992   .00000
    5     .00288   45.420    .63702   .00007   .00001   .00039   .19110   .00000
    6     .00000 8796.670    .24127   .99991   .99997   .99701   .00218  1.00000


End Block Number   1   All requested variables entered.

22 Dec 99   Multiple Collinearity Example                                                                                     Page 5
17:49:22    UCLA OAC                       IBM RS6000       AIX 3.2.5/4.


Preceding task required .27 seconds CPU time;  .50 seconds elapsed.

  46  0  Regression variables=gpa,greq,grev,mat,ar
  47  0          /descriptives=mean,stddev,corr,n
  48  0          /statistics=r,anova,cha,coeff,ci,collin,tol,history
  49  0          /dependent=gpa
  50  0      /method=enter.
  51  0

     1908 bytes of memory required for REGRESSION procedure.
        0 more bytes may be needed for Residuals plots.



22 Dec 99   Multiple Collinearity Example                                                                                     Page 6
17:49:22    UCLA OAC                       IBM RS6000       AIX 3.2.5/4.


                                     * * * *   M U L T I P L E   R E G R E S S I O N   * * * *


Listwise Deletion of Missing Data

             Mean  Std Dev  Label

GPA         3.313     .600
GREQ      565.333   48.618
GREV      575.333   83.034
MAT        67.000    9.248
AR          3.567     .838

N of Cases =    30

Correlation:

                GPA       GREQ       GREV        MAT         AR

GPA           1.000       .611       .581       .604       .621
GREQ           .611      1.000       .468       .267       .508
GREV           .581       .468      1.000       .426       .405
MAT            .604       .267       .426      1.000       .525
AR             .621       .508       .405       .525      1.000


22 Dec 99   Multiple Collinearity Example                                                                                     Page 7
17:49:22    UCLA OAC                       IBM RS6000       AIX 3.2.5/4.


                                     * * * *   M U L T I P L E   R E G R E S S I O N   * * * *

Equation Number 1    Dependent Variable..   GPA

  Descriptive Statistics are printed on Page    6

Block Number  1.  Method:  Enter


Variable(s) Entered on Step Number  1..    AR
                                    2..    GREV
                                    3..    MAT
                                    4..    GREQ


Multiple R           .80030                                             Analysis of Variance
R Square             .64047          R Square Change    .64047                              DF      Sum of Squares      Mean Square
Adjusted R Square    .58295          F Change         11.13400          Regression           4             6.68313          1.67078
Standard Error       .38738          Signif F Change    .0000           Residual            25             3.75153           .15006

                                                                        F =      11.13400       Signif F =  .0000


------------------------------------------ Variables in the Equation ------------------------------------------

Variable              B        SE B     95% Confdnce Intrvl B       Beta  Tolerance        VIF         T  Sig T

GREQ            .003998     .001831  2.27987E-04      .007769    .324062    .653236      1.531     2.184  .0385
GREV            .001524     .001050 -6.39208E-04      .003687    .210912    .680518      1.469     1.451  .1593
MAT             .020896     .009549      .001230      .040562    .322145    .663614      1.507     2.188  .0382
AR              .144234     .113001     -.088497      .376964    .201604    .576442      1.735     1.276  .2135
(Constant)    -1.738107     .950740    -3.696192      .219979                                     -1.828  .0795


Collinearity Diagnostics

Number  Eigenval     Cond  Variance Proportions
                    Index  Constant     GREQ     GREV      MAT       AR
    1    4.94514    1.000    .00022   .00019   .00054   .00049   .00117
    2     .03083   12.665    .02767   .00671   .01992   .00074   .71464
    3     .01093   21.267    .04052   .00000   .76228   .32693   .00412
    4     .01038   21.831    .07780   .10418   .15699   .54448   .08140
    5     .00272   42.653    .85379   .88892   .06027   .12736   .19868


End Block Number   1   All requested variables entered.

22 Dec 99   Multiple Collinearity Example                                                                                     Page 8
17:49:22    UCLA OAC                       IBM RS6000       AIX 3.2.5/4.


                                     * * * *   M U L T I P L E   R E G R E S S I O N   * * * *

Equation Number 1    Dependent Variable..   GPA


                                                       Summary table
                                                       -------------

Step   MultR     Rsq  AdjRsq    F(Eqn)  SigF   RsqCh       FCh SigCh       Variable  BetaIn  Correl
   1                                                                  In:  AR         .6207   .6207
   2                                                                  In:  GREV       .3947   .5815
   3                                                                  In:  MAT        .2900   .6042
   4   .8003   .6405   .5829    11.134  .000   .6405    11.134  .000  In:  GREQ       .3241   .6111

22 Dec 99   Multiple Collinearity Example                                                                                     Page 9
17:49:22    UCLA OAC                       IBM RS6000       AIX 3.2.5/4.


Preceding task required .00 seconds CPU time;  .02 seconds elapsed.

  52  0

    51 command lines read.
     0 errors detected.
     0 warnings issued.
     0 seconds CPU time.
     1 seconds elapsed time.
       End of job.