Finding the estimated variance of residuals

[Bas Boomen]

Hello,

I am fairly new to Stata and I have a question which I hope can be answered via this forum.

I ran a simple OLS regression in the form

reg y1 x1 x2, robust

in which I added time dummies as independent variables for the years 2009-2019. Now I want to obtain 'the estimated variances of residuals' (sigma_hat^2) for each of the years. I think this means that I should run separate regressions for each of the years, excluding the others. However, I don't know how or where I can find the estimated variance of residuals of the different years?

Do I have to look at the Root MSE?

I hope someone can help me with this.

Kind regards,

Bas van den Boomen

[Carlo Lazzaro]

Bas:
welcome to this forum.
Stata returns the standard error of the residuals (that you can square to obtain the variance).

. use "C:\Program Files (x86)\Stata15\ado\base\a\auto.dta"
(1978 Automobile Data)

. reg price mpg i.foreign

      Source |       SS           df       MS      Number of obs   =        74
-------------+----------------------------------   F(2, 71)        =     14.07
       Model |   180261702         2  90130850.8   Prob > F        =    0.0000
    Residual |   454803695        71  6405685.84   R-squared       =    0.2838
-------------+----------------------------------   Adj R-squared   =    0.2637
       Total |   635065396        73  8699525.97   Root MSE        =    2530.9

------------------------------------------------------------------------------
       price |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         mpg |  -294.1955   55.69172    -5.28   0.000    -405.2417   -183.1494
             |
     foreign |
    Foreign  |   1767.292    700.158     2.52   0.014     371.2169    3163.368
       _cons |   11905.42   1158.634    10.28   0.000     9595.164    14215.67
------------------------------------------------------------------------------

. predict residual, residuals

. predict se_residual, stdr

. list residual se_residual in 1/10

     +----------------------+
     |  residual   se_res~l |
     |----------------------|
  1. | -1334.114   2503.568 |
  2. | -2155.091   2501.542 |
  3. | -1634.114   2503.568 |
  4. | -1205.505   2506.473 |
  5. |  334.5177   2492.034 |
     |----------------------|
  6. | -821.8957   2504.426 |
  7. |  196.6686   2482.802 |
  8. | -832.5046   2506.473 |
  9. |  3173.713   2497.414 |
 10. |   -2233.7   2506.068 |
     +----------------------+

.

If you add -i.year- among predcitors, you will have residuals related to all the regressors, including -i.year-, as they act adjusted for each other in your regressin model: hence, I'm not that clear with your second question..

[Bas Boomen]

Hello Carlo,

Thank you for your clarifying answer. This works for me.

Kind regards,

Bas