I have written a command to estimate robust variance post Seemingly Unrelated Regression.
Currently the program works like this:
Code:
. sysuse auto, clear (1978 Automobile Data) . sureg (price headroom) (mpg length weight), noheader ------------------------------------------------------------------------------ | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- price | headroom | 389.6366 401.1807 0.97 0.331 -396.663 1175.936 _cons | 4998.979 1247.577 4.01 0.000 2553.774 7444.185 -------------+---------------------------------------------------------------- mpg | length | -.0916353 .0539683 -1.70 0.090 -.1974113 .0141407 weight | -.0033167 .0015459 -2.15 0.032 -.0063467 -.0002868 _cons | 48.53323 5.936823 8.17 0.000 36.89727 60.16919 ------------------------------------------------------------------------------ . suregr2 Seemingly unrelated regression -------------------------------------------------------------------------- Equation Obs Parms RMSE "R-sq" chi2 P -------------------------------------------------------------------------- price 74 1 2910.242 0.0131 0.94 0.3314 mpg 74 2 3.34875 0.6604 136.53 0.0000 -------------------------------------------------------------------------- ------------------------------------------------------------------------------ | Robust | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- price | headroom | 389.6366 295.9122 1.32 0.188 -190.3406 969.6139 _cons | 4998.979 843.8949 5.92 0.000 3344.976 6652.983 -------------+---------------------------------------------------------------- mpg | length | -.0916353 .0682694 -1.34 0.180 -.2254408 .0421703 weight | -.0033167 .0019688 -1.68 0.092 -.0071756 .0005422 _cons | 48.53323 7.544959 6.43 0.000 33.74538 63.32108 ------------------------------------------------------------------------------ .
How do you think is better, I keep it as it is now, or I make it as a prefix command, something like:
Code:
suregr2: sureg (price headroom) (mpg length weight), noheader
0 Response to To both experienced Stata programmers, and Stata users: How do you prefer to have the command, as a post estimation or as a prefix?
Post a Comment