Dear Allin,

Thanks for the answer. I have learned several things today by looking at the gnuplot file.

By the way, I would have an additional question. I have used the SVAR_cumulate command while estimating my Svar. Precisely, one of my time series is the growth rate of industrial production. Not surprisingly,  its IRF displays up and down movements. For sake of comparison, I have therefore plotted the cumulated irf.

However, it seems to me that now the magnitude of the response is too large. Why do I need to "cumulate" the time series before estimating the model? Is it right this procedure?

Thanks again.
Gabriela

On 14/05/2013 12:49 PM, "Allin Cottrell" <cottrell@wfu.edu> wrote:
On Tue, 14 May 2013, Gabriela Nodari wrote:

> I am dealing with a Svar model and I have plotted some impulse responses,
> obtained while doing a sensitivity analysis, all in the same graph.
>
> However,  I would like to plot also the corresponding confidence intervals.
> I have some idea about how to plot them with lines, but I would like to
> keep the baseline confidence interval as a shaded area, as it is by
> default.
>
> Is there a way to do this?

Yes, but you'll have to edit the gnuplot file yourself: save
the plot "as an icon", right click the plot icon, and select
Edit plot commands. Note that the Help button in that window
should bring up the gnuplot manual.

Allin Cottrell
_______________________________________________
Gretl-users mailing list
Gretl-users@lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users