finding rho from xtsur

[Jane Fry]

Hi,

I am running the following model on Stata15:

xtsur (unableheat nomeal temp_shock $rhs $beds $states $waves) ///
      (nomeal unableheat temp_shock $rhs $beds $states $waves) ///
      if type==0 & wave>=11

and would like to get the estimate of rho (correlation between errors in the two equations). How do I do this? I can't find any stored result to use.

Thanks for your help.

Jane.

[Carlo Lazzaro]

Jane:
from the -help file- of the community-contributed module -xtsur-, -e(sigma_e)- is possibly what you're looking for:

. sysuse xtsur_example.dta

. xtsur (y1 x1 x2 x3 x4) (y2 x4 x6 x7) (y3 x7 x9)
(running multi-step estimates...)

Calculating multi-step estimates...
Iteration   1 : relative difference =  16.292048
Iteration   2 : relative difference =  4.866e-09


Seemingly unrelated regression (SUR) in panel data set

One-way random effect estimation:
------------------------------------------------------------------------------
Number of Group variable:   14                  Number of obs      =      1672
Panel variable: PanelID                         Number of eqn      =         3
Time variable : year                            Number of panels   =        14

Random effects u_i ~ Gaussian
corr(u_i, e_it)    = 0 (assumed)
Panel type         : unbalanced

------------------------------------------------------------------------------
             | Coefficient  Std. err.      z    P>|z|     [95% conf. interval]
-------------+----------------------------------------------------------------
y1           |
          x1 |   4.786022   .0039476  1212.39   0.000     4.778285    4.793759
          x2 |   .0061446   1.74e-07  3.5e+04   0.000     .0061442    .0061449
          x3 |  -.1236683   .0000234 -5290.42   0.000    -.1237141   -.1236225
          x4 |   .2942481   .0000859  3424.71   0.000     .2940797    .2944165
-------------+----------------------------------------------------------------
y2           |
          x4 |   16.32775    .021115   773.28   0.000     16.28636    16.36913
          x6 |  -525.6866    .655111  -802.44   0.000    -526.9706   -524.4026
          x7 |  -435.8584   1.983139  -219.78   0.000    -439.7452   -431.9715
-------------+----------------------------------------------------------------
y3           |
          x7 |   .8733527   738.0142     0.00   0.999    -1445.608    1447.355
          x9 |  -.0531212   180.5034    -0.00   1.000    -353.8333    353.7271
-------------+----------------------------------------------------------------
     sigma_u |   see e(sigma_u)
     sigma_e |   see e(sigma_e)
------------------------------------------------------------------------------
Dependent variables:   y1 y2 y3
Independent variables: x1 x2 x3 x4 x6 x7 x9
------------------------------------------------------------------------------

. mat list e(sigma_e)

symmetric e(sigma_e)[3,3]
           c1         c2         c3
r1  3916396.3
r2  1.186e+09  6.773e+11
r3  13.389187  40103.195  7.3329205

.

[Jane Fry]

Thanks!