Am 09.02.2015 um 22:58 schrieb alexkakashi(a)libero.it:
Hi,
I have a question about the VAR models. I have two annual time series
from 1880 to 2011. I set the range of the sample from 1882 to 1970. Then
a VAR(2) model is estimated, but in the OLS estimates are considered 89
observations (from 1882 to 1970) and not the observation from 1884 to 1970.
How can I solve this problem?
Well if you want to use the obs only from 1884, how about setting your
sample start to ... ahem, 1884?
More seriously, yes there is an ambiguity about whether pre-sample
values should be used for lagged values or not. The convention in gretl
is to use them whenever they're available.
hth,
sven