*
* Example 8.2 from page 155
*
open data tablef5-1[1].txt
calendar(q) 1950
data(format=prn,org=columns) 1950:1 2000:4 year qtr realgdp realcons realinvs realgovt realdpi $
   cpi_u m1 tbilrate unemp pop infl realint
*
* Do the two hypothesized regressions. Put the fitted values for the first into
* fit0, and the second into fit1.
*
linreg realcons
# constant realdpi{0 1}
prj fit0
linreg realcons
# constant realdpi realcons{1}
prj fit1
*
* Rerun the first regression, adding fit1 as an explanatory variable. The
* J-statistic is the t on the auxiliary variable.
*
linreg realcons
# constant realdpi{0 1} fit1
*
* Now rerun the second regression, adding fit0.
*
linreg realcons
# constant realdpi realcons{1} fit0