Post-estimation commands to calculate the contribution of each regressor

[Alessandro Franconi]

Hi Statalists,

I am trying to estimate the contribution of each regressor after a regression of the form:

reg Y x1 x2 x3 x4 x5 x6 x7 x8 x9 x10 if ID=="1"

basically I would like to have
contrib_x_1_ID1 = beta_1*x_1
contrib_x_2_ID1 =beta_2*x_2
...
contrib_x_10_ID1 =beta_10*x_10

This is something I can do easily. The problem is that I have a panel of countries, however the regression is estimated at a country-level (ID) for each ID. This complicates a bit the calculation of the contribution of each regressor after each regression withour a proper command.

So, the question is: is there a post-estimation command that does it automatically after each regression?

Thanks
Ale

[Alessandro Franconi]

The way I solve the issue "manually":

local i=1
foreach var in x1 x2 x3 x4 x5 x6 x7 x8 x9 x10 {
    gen coeff_`var'_1 = e(b)[1,`i'] if ID1=="1"
    gen contr_`var'_1 = `var'*coeff_`var'_1 if ID1=="1"
    local ++i  /* this increase the counter at each iteration */
}