Announcement

Collapse
No announcement yet.
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • Report Bonferroni adjusted p-values after reg

    Hello,
    I am running a series of regressions and I would like to report the results using Bonferroni-adjusted p-values.

    My data looks something like this, and I run 3 regressions on 3 different dependent variables and 4 different regressors:

    Code:
    sysuse auto
    gen log_price=log(price)
    gen sqrt_price=sqrt(price)
    
    reg price mpg rep78 i.foreign weight
    eststo reg1
    reg log_price mpg rep78 i.foreign weight
    eststo reg2
    reg sqrt_price mpg rep78 i.foreign weight
    eststo reg3
    esttab reg1 reg2 reg3
    
    ------------------------------------------------------------
                          (1)             (2)             (3)   
                        price       log_price      sqrt_price   
    ------------------------------------------------------------
    mpg                 27.32        -0.00148          0.0445   
                       (0.35)         (-0.15)          (0.11)   
    
    rep78               121.1          0.0336           1.069   
                       (0.36)          (0.81)          (0.59)   
    
    0.foreign               0               0               0   
                          (.)             (.)             (.)   
    
    1.foreign          3520.3***        0.508***        20.84***
                       (4.11)          (4.75)          (4.45)   
    
    weight              3.565***     0.000469***       0.0201***
                       (5.42)          (5.72)          (5.60)   
    
    _cons             -6729.6           6.979***        4.697   
                      (-1.95)         (16.23)          (0.25)   
    ------------------------------------------------------------
    N                      69              69              69   
    ------------------------------------------------------------
    t statistics in parentheses
    * p<0.05, ** p<0.01, *** p<0.001
    Ideally, the final table should show Bonferroni adjusted p-values under the standard errors.
    Does anyone know how I can do this?

    thanks a lot

  • #2
    Tom:
    why not considering -sureg-?
    Code:
    sysuse auto
    gen log_price=log(price)
    gen sqrt_price=sqrt(price)
    sureg (price mpg rep78 i.foreign weight) ( log_price mpg rep78 i.foreign weight) ( sqrt_price mpg rep78 i.foreign weight), small dfk
    sureg (price mpg rep78 i.foreign weight) ( log_price mpg rep78 i.foreign weight) ( sqrt_price mpg rep78 i.foreign weight), small dfk
    
    Seemingly unrelated regression
    ------------------------------------------------------------------------------
    Equation             Obs   Params         RMSE  "R-squared"         F      P>F
    ------------------------------------------------------------------------------
    price                 69        4     2128.805      0.4972      15.82   0.0000
    log_price             69        4     .2652663      0.5601      20.37   0.0000
    sqrt_price            69        4      11.6224      0.5319      18.18   0.0000
    ------------------------------------------------------------------------------
    
    ------------------------------------------------------------------------------
                 | Coefficient  Std. err.      t    P>|t|     [95% conf. interval]
    -------------+----------------------------------------------------------------
    price        |
             mpg |   27.32371   77.53757     0.35   0.725    -125.6111    180.2585
           rep78 |   121.1322   334.3828     0.36   0.718    -538.4032    780.6677
                 |
         foreign |
        Foreign  |   3520.324    857.318     4.11   0.000     1829.353    5211.295
          weight |   3.565247   .6582976     5.42   0.000     2.266823    4.863671
           _cons |   -6729.56   3450.835    -1.95   0.053    -13535.98     76.8546
    -------------+----------------------------------------------------------------
    log_price    |
             mpg |  -.0014765   .0096618    -0.15   0.879    -.0205334    .0175804
           rep78 |   .0335949   .0416668     0.81   0.421    -.0485886    .1157783
                 |
         foreign |
        Foreign  |   .5077989   .1068288     4.75   0.000     .2970902    .7185076
          weight |   .0004692    .000082     5.72   0.000     .0003074     .000631
           _cons |   6.979208    .430002    16.23   0.000     6.131073    7.827342
    -------------+----------------------------------------------------------------
    sqrt_price   |
             mpg |   .0444727   .4233235     0.11   0.916     -.790489    .8794345
           rep78 |   1.069119   1.825593     0.59   0.559    -2.531675    4.669913
                 |
         foreign |
        Foreign  |   20.83803   4.680606     4.45   0.000     11.60602    30.07004
          weight |    .020133    .003594     5.60   0.000     .0130441    .0272219
           _cons |   4.696691   18.84015     0.25   0.803    -32.46355    41.85694
    ------------------------------------------------------------------------------
    
    .
    Kind regards,
    Carlo
    (Stata 19.0)

    Comment

    Working...
    X