.-
help for ^vif^                                               (STB-25: sg32.1)
.-

Variance inflation factors
--------------------------

        vif


Description
-----------

vif calculates the variance inflation factors for the independent variables
in a linear regression model. This command must follow a call to fit.


Remarks
-------

In general, a variance inflation factor above 10 is considered evidence of
multicollinearity in the model. Other analysts use 1/VIF and compare to a
tolerance level in order to assess whether a predictor is included in the model
or not.

The mean value of the variance inflation factors also provides useful
information about the effect of the multicollinearity on the sum of squared
errors. Mean VIF values considerably larger than 1 are indicative of serious
multicollinearity problems.


Example
-------

 . ^de^

Contains data from /usr/local/stata/auto.dta
  Obs:    74 (max= 12688)                     1978 Automobile Data
 Vars:    12 (max=   200)
Width:    44 (max=   802)
  1. make         str18  %18s                 Make and Model
  2. price        int    %8.0g                Price
  3. mpg          int    %8.0g                Mileage (mpg)
  4. rep78        int    %8.0g                Repair Record 1978
  5. hdroom       float  %6.1f                Headroom (in.)
  6. trunk        int    %8.0g                Trunk space (cu. ft.)
  7. weight       int    %8.0g                Weight (lbs.)
  8. length       int    %8.0g                Length (in.)
  9. turn         int    %8.0g                Turn Circle (ft.)
 10. displ        int    %8.0g                Displacement (cu. in.)
 11. gratio       float  %6.2f                Gear Ratio
 12. foreign      int    %8.0g       foreign  Car type
Sorted by:  foreign


 . ^fit price mpg rep78 trunk hdroom length turn displ gratio^

  Source |       SS       df       MS                  Number of obs =      69
---------+------------------------------               F(  8,    60) =    6.33
   Model |   264102049     8  33012756.2               Prob > F      =  0.0000
Residual |   312694909    60  5211581.82               R-squared     =  0.4579
---------+------------------------------               Adj R-squared =  0.3856
   Total |   576796959    68  8482308.22               Root MSE      =  2282.9

------------------------------------------------------------------------------
   price |      Coef.   Std. Err.       t     P>|t|       [95% Conf. Interval]
---------+--------------------------------------------------------------------
     mpg |    -144.84   82.12751     -1.764   0.083      -309.1195    19.43947
   rep78 |   727.5783   337.6107      2.155   0.035       52.25641      1402.9
   trunk |   44.02061    108.141      0.407   0.685      -172.2935    260.3347
  hdroom |  -807.0996   435.5802     -1.853   0.069       -1678.39    64.19057
  length |  -8.688914   34.89848     -0.249   0.804      -78.49626    61.11843
    turn |  -177.9064   137.3455     -1.295   0.200      -452.6382     96.8255
   displ |   30.73146   7.576952      4.056   0.000        15.5753    45.88762
  gratio |   1500.119   1110.959      1.350   0.182      -722.1302    3722.368
   _cons |   6691.976   7457.906      0.897   0.373      -8226.057    21610.01
------------------------------------------------------------------------------

 . ^vif^

Variable |      VIF      1/VIF
---------+----------------------
     mpg |      3.03    0.330171
   rep78 |      1.46    0.686147
   trunk |      2.88    0.347444
  hdroom |      1.80    0.554917
  length |      8.22    0.121614
    turn |      4.85    0.205997
   displ |      6.50    0.153860
  gratio |      3.45    0.290068
---------+----------------------
Mean VIF |      4.02


Author
------
        James W. Hardin, Stata Corporation
        stata@@stata.com


See Also
--------

    STB: STB-25 sg32.1, STB-24 sg32
 Manual: [5s] fit
On-line: @fit@