Calculating the mean of a coefficient of SUR regression

[Oscar Damgaard]

Hello,

I am performing an event study using SUR regression, where the abnormal stock return is shown by the coefficient "dummyEvent". The output shown below is a subset of 3 out of a total of 85 firms for which the SUR is run. Now I would like to calculate the average of the coefficient "dummyEvent" of all 85 regressions of the SUR and store it in a new variable. Reading other threads and Stata's help page, I came across the possibility to read out the individual coefficients via the following code.

matrix b = e(b)
display el(b,1,3) el(b,1,7) el(b,1,11)

One could sum the coefficients and divide by the number of companies, however this procedure is cumbersome for 85 companies in the SUR regression. Does anyone have any ideas on how to solve it more efficiently? Maybe with a foreach loop?

 






Coef.
Std. Err.
z
P>z
[Interval]








Amazon






Dow Jones
.5122257
.0651809
7.86
0.000
.3844734
.639978

dummyDayBefore
-.0005352
.0069166
-0.08
0.938
-.0140915
.0130212

dummyEvent
.0023194
.0069305
0.33
0.738
-.0112642
.0159029

_cons
-.0005643
.0006683
-0.84
0.398
-.0018742
.0007455









Tesla







DowJones
1.542822
.0984094
15.68
0.000
1.349943
1.735701

dummyDayBefore
-.0095792
.0104426
-0.92
0.359
-.0300464
.0108879

dummyEvent
.0006608
.0104636
0.06
0.950
-.0198475
.0211691

_cons
-.0008611
.001009
-0.85
0.393
-.0028387
.0011164









Apple







DowJones
1.169062
.1275515
9.17
0.000
.9190661
1.419059

dummyDayBefore
.0157705
.013535
1.17
0.244
-.0107576
.0422986

dummyEvent
.0132543
.0135622
0.98
0.328
-.0133271
.0398357

_cons
-.0016939
.0013078
-1.30
0.195
-.0042571
.0008693

Best,
Oscar

[Andrew Musau]

sysuse auto, clear
sureg (price foreign weight length) (mpg foreign weight) (displ foreign weight)
mat b=e(b)
local coleqs: coleq(b)
local coleqs: list uniq coleqs
*e.g., average "foreign" and "weight" coefficients across equations
foreach eq of local coleqs{
    di "equation is for `eq' "
    margins, expression(0.5*_b[`eq':foreign] + 0.5*_b[`eq':weight])
}

Res.:

. sureg (price foreign weight length) (mpg foreign weight) (displ foreign weight)

Seemingly unrelated regression
--------------------------------------------------------------------------
Equation             Obs   Parms        RMSE    "R-sq"       chi2        P
--------------------------------------------------------------------------
price                 74       3    1967.769    0.5488      89.74   0.0000
mpg                   74       2    3.337283    0.6627     145.39   0.0000
displacement          74       2    39.60002    0.8115     318.62   0.0000
--------------------------------------------------------------------------

------------------------------------------------------------------------------
             |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
price        |
     foreign |    3575.26   621.7961     5.75   0.000     2356.562    4793.958
      weight |   5.691462   .9205043     6.18   0.000     3.887307    7.495618
      length |  -88.27114    31.4167    -2.81   0.005    -149.8467   -26.69554
       _cons |   4506.212   3588.044     1.26   0.209    -2526.225    11538.65
-------------+----------------------------------------------------------------
mpg          |
     foreign |  -1.650029   1.053958    -1.57   0.117    -3.715748    .4156902
      weight |  -.0065879   .0006241   -10.56   0.000     -.007811   -.0053647
       _cons |    41.6797   2.121197    19.65   0.000     37.52223    45.83717
-------------+----------------------------------------------------------------
displacement |
     foreign |   -25.6127   12.50621    -2.05   0.041    -50.12441   -1.100984
      weight |   .0967549   .0074051    13.07   0.000     .0822411    .1112686
       _cons |  -87.23548   25.17001    -3.47   0.001    -136.5678   -37.90317
------------------------------------------------------------------------------


equation is for price 
Warning: expression() does not contain predict() or xb().
Warning: prediction constant over observations.

Predictive margins                              Number of obs     =         74

Expression   : 0.5*_b[price:foreign] + 0.5*_b[price:weight]

------------------------------------------------------------------------------
             |            Delta-method
             |     Margin   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
       _cons |   1790.476   310.9925     5.76   0.000     1180.942     2400.01
------------------------------------------------------------------------------
equation is for mpg 
Warning: expression() does not contain predict() or xb().
Warning: prediction constant over observations.

Predictive margins                              Number of obs     =         74

Expression   : 0.5*_b[mpg:foreign] + 0.5*_b[mpg:weight]

------------------------------------------------------------------------------
             |            Delta-method
             |     Margin   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
       _cons |  -.8283085   .5271639    -1.57   0.116    -1.861531    .2049138
------------------------------------------------------------------------------
equation is for displacement 
Warning: expression() does not contain predict() or xb().
Warning: prediction constant over observations.

Predictive margins                              Number of obs     =         74

Expression   : 0.5*_b[displacement:foreign] + 0.5*_b[displacement:weight]

------------------------------------------------------------------------------
             |            Delta-method
             |     Margin   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
       _cons |  -12.75797   6.255299    -2.04   0.041    -25.01813   -.4978111
------------------------------------------------------------------------------

.

[Oscar Damgaard]

Hello Andrew,

thank you for your helpful reply. Unfortunately, when I run your code, I don't get any output, Stata just shows that the code has been run (see attached output).

. matrix b=e(b)

. local coleqs: coleq(b)

. local coleqs: list uniq colegs

. foreach eq of local coleqs{
  2.         di "equation is for `eq' "
  3.     margins, expression(0.5*_b[`eq':dummyDayBefore] + 0.5*_b[`eq':dummyEvent])
  4. }

Do you know what could be the reason for this? I have specified my SUR regression as follows:

local subsetvar Amazon-Apple
sureg (`subsetvar' = DowJones-dummyEvent) if inrange(mdy(Month,Day,Year),mdy(9,1,2010),mdy(2,8,2011))

Thank you very much,
Oscar

[Andrew Musau]

My apologies Oscar Damgaard, I completely missed your response. It looks like you have a typo in your code:

. matrix b=e(b) . local coleqs: coleq(b)
. local coleqs: list uniq colegs
. foreach eq of local coleqs{ 2
. di "equation is for `eq' " 3
. margins, expression(0.5*_b[`eq':dummyDayBefore] + 0.5*_b[`eq':dummyEvent]) 4
. }

should be "coleqs"