Dear all,

I need to compute and plot the impulse response function for a simple estimated AR(4) process. I am using Stata 8.2. I know about -irf create- after var, but this does not work if I estimate a simple AR(4):

. var growth, lags(4 3 2 1)

Vector autoregression

Sample:  1961:2   2003:2                           No. of obs      =       169
Log likelihood =  573.9452                         AIC             = -6.733079
FPE            =  .0000697                         HQIC            =   -6.6955
Det(Sigma_ml)  =  .0000657                         SBIC            = -6.640478

Equation           Parms      RMSE     R-sq      chi2     P>chi2
----------------------------------------------------------------
growth                5     .008229   0.1144   21.82736   0.0002
----------------------------------------------------------------
------------------------------------------------------------------------------
            |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
growth       |
growth       |
         L1 |   .2699427   .0768728     3.51   0.000     .1192748    .4206106
         L2 |   .1447093   .0784949     1.84   0.065     -.009138    .2985566
         L3 |  -.0307757   .0783419    -0.39   0.694     -.184323    .1227715
         L4 |   .0102891   .0754549     0.14   0.892    -.1375998     .158178
_cons        |   .0050361   .0010889     4.62   0.000     .0029018    .0071703
------------------------------------------------------------------------------

. irf create irfresults, set(results, replace) step(24)
(file results.irf created)
(file results.irf now active)
invalid syntax
r(198);

The same for -varbasic-.

How can it be done in Stata?
Thanks for any hints,
best regards,

Eva Poen