Announcement

Collapse
No announcement yet.
X
Collapse
  • Page of 1
  • Filter
  • Time
  • Show
Clear All
new posts
  • #1

    Extracting Output Matrix From ivreghdfe

    I'm trying to extract coefficients, standard errors and p-values from a a regression run with ivreghdfe. With the standard reghdfe, it's easy enough:

    Code:
     
 reghdfe price mpg weight, noabsorb
(MWFE estimator converged in 1 iterations)

HDFE Linear regression                            Number of obs   =         74
Absorbing 1 HDFE group                            F(   2,     71) =      14.74
                                                  Prob > F        =     0.0000
                                                  R-squared       =     0.2934
                                                  Adj R-squared   =     0.2735
                                                  Within R-sq.    =     0.2934
                                                  Root MSE        =  2514.0286

------------------------------------------------------------------------------
       price |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         mpg |  -49.51222   86.15604    -0.57   0.567    -221.3025     122.278
      weight |   1.746559   .6413538     2.72   0.008      .467736    3.025382
       _cons |   1946.069    3597.05     0.54   0.590    -5226.245    9118.382
------------------------------------------------------------------------------

. mat OUTPUT = r(table)

. mat li OUTPUT

OUTPUT[9,3]
               mpg      weight       _cons
     b  -49.512221   1.7465592   1946.0687
    se   86.156039   .64135379   3597.0496
     t  -.57468079   2.7232382   .54101802
pvalue   .56732373   .00812981   .59018863
    ll  -221.30248   .46773602  -5226.2445
    ul   122.27804   3.0253823   9118.3819
    df          71          71          71
  crit   1.9939434   1.9939434   1.9939434
 eform           0           0           0

    But r(table) doesn't exist when using ivreghdfe. I think in part this is because ivreghdfe is a version of ivreg2. One can extract the first stage from ivreg2 like so:

    Code:
      
 sysuse auto ivreg2 price (mpg=weight), savefirst estimates replay _ivreg2_mpg mat l r(table)

    When replacing
    Code:
      estimates replay _ivreg2_mpg
    with
    Code:
      estimates replay _ivreg2_ price
    to get the first stage, stata tells me the _ivreg2_price is not found. Is there an easy way to extract model statistics from ivreg2 and ivreghdfe that I'm not seeing?
    Tags: ivreg2, ivreghdfe
  • #2
    For -ivreg2, you can store and retrieve first- and second-stage results like this:

    Code:
    Code:
    sysuse auto, clear
ivreg2 price (mpg=weight), savefirst
est store stage2
est dir

*    You can replay either of the equations like this:
est replay _ivreg2_mpg
est replay stage2

*    You can tabulate the two regression results like this
est table _ivreg2_mpg stage2 , se 

return list

*    Estimates table has the added benefit of producing r(coef): 
matlist r(coef)
    Results:
    Code:
    . sysuse auto, clear
(1978 automobile data)

. ivreg2 price (mpg=weight), savefirst

Stored estimation results
-------------------------
--------------------------------------------------------------------------
             |           Dependent  Number of        
        Name | Command    variable     param.  Title 
-------------+------------------------------------------------------------
 _ivreg2_mpg | ivreg2          mpg          2  First-stage regression: mpg
--------------------------------------------------------------------------

IV (2SLS) estimation
--------------------

Estimates efficient for homoskedasticity only
Statistics consistent for homoskedasticity only

                                                      Number of obs =       74
                                                      F(  1,    72) =    25.48
                                                      Prob > F      =   0.0000
Total (centered) SS     =  635065396.1                Centered R2   =   0.1801
Total (uncentered) SS   =   3447834321                Uncentered R2 =   0.8490
Residual SS             =  520685110.7                Root MSE      =     2653

------------------------------------------------------------------------------
       price | Coefficient  Std. err.      z    P>|z|     [95% conf. interval]
-------------+----------------------------------------------------------------
         mpg |  -340.1846   66.48161    -5.12   0.000    -470.4861    -209.883
       _cons |   13410.27   1449.068     9.25   0.000     10570.15    16250.39
------------------------------------------------------------------------------
Underidentification test (Anderson canon. corr. LM statistic):          48.213
                                                   Chi-sq(1) P-val =    0.0000
------------------------------------------------------------------------------
Weak identification test (Cragg-Donald Wald F statistic):              134.618
Stock-Yogo weak ID test critical values: 10% maximal IV size             16.38
                                         15% maximal IV size              8.96
                                         20% maximal IV size              6.66
                                         25% maximal IV size              5.53
Source: Stock-Yogo (2005).  Reproduced by permission.
------------------------------------------------------------------------------
Sargan statistic (overidentification test of all instruments):           0.000
                                                 (equation exactly identified)
------------------------------------------------------------------------------
Instrumented:         mpg
Excluded instruments: weight
------------------------------------------------------------------------------

. est store stage2

. est dir

--------------------------------------------------------------------------
             |           Dependent  Number of        
        Name | Command    variable     param.  Title 
-------------+------------------------------------------------------------
 _ivreg2_mpg | ivreg2          mpg          2  First-stage regression: mpg
      stage2 | ivreg2        price          2  IV (2SLS) estimation
--------------------------------------------------------------------------

. 
. *       You can replay either of the equations like this:
. est replay _ivreg2_mpg

------------------------------------------------------------------------------------------------------------------------
Model _ivreg2_mpg (First-stage regression: mpg)
------------------------------------------------------------------------------------------------------------------------

First-stage regression of mpg:

Statistics consistent for homoskedasticity only
Number of obs =                     74
------------------------------------------------------------------------------
         mpg | Coefficient  Std. err.      t    P>|t|     [95% conf. interval]
-------------+----------------------------------------------------------------
      weight |  -.0060087   .0005179   -11.60   0.000    -.0070411   -.0049763
       _cons |   39.44028   1.614003    24.44   0.000     36.22283    42.65774
------------------------------------------------------------------------------

. est replay stage2

------------------------------------------------------------------------------------------------------------------------
Model stage2
------------------------------------------------------------------------------------------------------------------------

Stored estimation results
-------------------------
--------------------------------------------------------------------------
             |           Dependent  Number of        
        Name | Command    variable     param.  Title 
-------------+------------------------------------------------------------
 _ivreg2_mpg | ivreg2          mpg          2  First-stage regression: mpg
--------------------------------------------------------------------------

IV (2SLS) estimation
--------------------

Estimates efficient for homoskedasticity only
Statistics consistent for homoskedasticity only

                                                      Number of obs =       74
                                                      F(  1,    72) =    25.48
                                                      Prob > F      =   0.0000
Total (centered) SS     =  635065396.1                Centered R2   =   0.1801
Total (uncentered) SS   =   3447834321                Uncentered R2 =   0.8490
Residual SS             =  520685110.7                Root MSE      =     2653

------------------------------------------------------------------------------
       price | Coefficient  Std. err.      z    P>|z|     [95% conf. interval]
-------------+----------------------------------------------------------------
         mpg |  -340.1846   66.48161    -5.12   0.000    -470.4861    -209.883
       _cons |   13410.27   1449.068     9.25   0.000     10570.15    16250.39
------------------------------------------------------------------------------
Underidentification test (Anderson canon. corr. LM statistic):          48.213
                                                   Chi-sq(1) P-val =    0.0000
------------------------------------------------------------------------------
Weak identification test (Cragg-Donald Wald F statistic):              134.618
Stock-Yogo weak ID test critical values: 10% maximal IV size             16.38
                                         15% maximal IV size              8.96
                                         20% maximal IV size              6.66
                                         25% maximal IV size              5.53
Source: Stock-Yogo (2005).  Reproduced by permission.
------------------------------------------------------------------------------
Sargan statistic (overidentification test of all instruments):           0.000
                                                 (equation exactly identified)
------------------------------------------------------------------------------
Instrumented:         mpg
Excluded instruments: weight
------------------------------------------------------------------------------

. 
. *       You can tabulate the two regression results like this
. est table _ivreg2_mpg stage2 , se 

----------------------------------------
    Variable | _ivreg2_~g     stage2    
-------------+--------------------------
      weight | -.00600869               
             |  .00051788               
         mpg |              -340.18458  
             |               66.481609  
       _cons |  39.440284    13410.269  
             |  1.6140031    1449.0677  
----------------------------------------
                            Legend: b/se

. 
. return list

macros:
              r(names) : "_ivreg2_mpg stage2"

matrices:
               r(coef) :  3 x 4

. 
. *       Estimates table has the added benefit of producing r(coef): 
. matlist r(coef)

             | _ivreg2~g            | stage2               
             |         b        var |         b        var 
-------------+----------------------+----------------------
      weight | -.0060087   2.68e-07 |        .z         .z 
         mpg |        .z         .z | -340.1846   4419.804 
       _cons |  39.44028   2.605006 |  13410.27    2099797
    Does this help?

    Comment

    Previous Next
    Working...
    X