Forecasting Code with constrained regression

[Gabriele Colombo]

Hi folks,
I am new on the forum and to be honest I am not an expert of Stata either.
I am performing for my master thesis out of sample forecasts with rolling technique. I got stuck on running the following code which is aimed to include a constrained regression


constraint define 1 l.PPP_2=0.840896415253715
program fcst_ppcad, rclass
syntax [if]

qui tsset
local timevar `r(timevar)'
local first `r(tmin)'

cnsreg PPP l.PPP_2, constraints(l.PPP_2=0.84089) `if'
summarize `timevar' if e(sample)

local last = `r(max)' -`first'+1
local fcast = _b[_cons] + _b[l.PPP_2]* ///
PPP_2[`last']

return scalar fcast= `fcast'
return scalar actual = PPP[`last'+1]
return scalar sqerror = (PPP[`last'+1]- ///
`fcast')^2
end

rolling pppcad_sqerr=r(sqerror) pppcad_fcast=r(fcast) actual=r(actual), window(148) saving(pppcad_q7, replace): fcst_ppcad


The objective would be to have the coefficient in the estimatie equal to 0.840896415253715 and this code doesn't work in the right manner.
Please, any suggestions is really appreciated.

Thanks!!!