Re: [Gretl-users] counting
On Mon, 4 Jan 2010, Berend Hasselman wrote:
You beat me to it.
I was getting some doubts about the genr's.
So I decided to initialise y to 0.
[...]
I've run this several times. The rejection rate still seems to
reach 6 or 7 %.
Slightly modified version:
<script>
set echo off
set messages off
nulldata 100
scalar n = 9
matrix alphas = 0.9 + 0.1/(n+1)*seq(0,n)
scalar rlevel = 0.05
scalar N = 1000
matrix rjs = zeros(1, cols(alphas))
set stopwatch
loop for i=0..n --quiet
scalar reject = 0
alpha = alphas[i+1]
loop N --quiet
series y = 0
genr y = alpha*y(-1) + normal()
adf 1 y --c --quiet
genr pv = $pvalue
reject += (pv<rlevel)
endloop
rjs[i+1] = reject
end loop
time=$stopwatch
results = (alphas | (100/N * rjs))'
colnames(results, "alpha rej_rate")
print results
printf "CPU seconds used %.2f\n",time
</script>
which of course illustrates the well known lack of power of the ADF test:
if you use "adf --gls" things change quite a bit.
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Università Politecnica delle Marche
r.lucchetti(a)univpm.it
http://www.econ.univpm.it/lucchetti