*
* Example 7.3 from page 224
*
open data jtrain.raw
data(format=free,org=columns) 1 471 year fcode employ sales avgsal scrap rework tothrs $
 union grant d89 d88 totrain hrsemp lscrap lemploy lsales lrework lhrsemp lscrap_1 grant_1 $
 clscrap cgrant clemploy clsales lavgsal clavgsal cgrant_1 chrsemp clhrsemp
*
* If they weren't provided on the data set, you could create the log variables by
*
set lsales = log(sales)
set lemploy = log(employ)
*
* The regression is to be run only over the 1988 data. There's already a dummy in
* the data set for this, so you just include the option smpl=d88. An alternative
* would be to include the option smpl=(year==1988). The == operator test for
* equality, giving 1 if the two are equal and 0 if not.
*
linreg(smpl=d88) hrsemp
# constant grant lsales lemploy