Thanks David.
I try to get the fcast graph for the endogenous variable that has
already been obtained from the fcast compute by writing:
fcast graph ay
and I get the weird message (weird because the variable has been
successfully placed on the dataset after I executed fcast compute)
variable ay_LB not found
r(111);
Note: I can't really think of anything to try besides generate once
again the variables.
Thank you
The first message
"asymptotic standard error not available with exogenous variables"
was produced because the formula for the asymptotic standard errors was
derived for the case in which there are no exogenous variables in the
VAR.
In this case, bootstrapped standard errors are still available.
The second message
"exogenous variables cannot be missing in the forecast period"
is the cause of the error code r(498). This message occurred because
some of
the exogenous variables are missing for part of the forecast horizon.
If
there are no observations on the exogenous variables, it is not possible
to
produce a forecast using the specified exogenous variables.
--David
[email protected]
-----Original Message-----
From: Demetriou, Eleftherios
Sent: Friday, August 14, 2009 5:03 PM
To: '[email protected]'
Subject: After usingVAR and FCAST COMPUTE I get an error message -
Asymptotic Standard Error
Hi,
I can't find anything anywhere to answer my question and I would really
appreciated any feedback if anyone faced the same problem.
I used
Var y x_1, exog(t tsquare feb-dec) lags(1/13)
fcast compute a, step(18)
and I received the following message:
asymptotic standard error not available with exogenous variables
exogenous variables cannot be missing in the forecast period
r(498)
Thank you
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
