Re: st: RE: interpretation of impulse response function results

[Yunxian Lu <yunxian.lu@gmail.com>]

Thanks! I really appreciate your help.

Best,
Yunxian

On Mon, Mar 14, 2011 at 4:55 AM, DE SOUZA Eric
<eric.de_souza@coleurope.eu> wrote:
> See pages 172 and 173 of the manual, esp. the second paragraph of page 173.
>
>
> Eric de Souza
> College of Europe
> Brugge (Bruges), Belgium
> http://www.coleurope.eu
>
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Yunxian Lu
> Sent: 14 March 2011 05:55
> To: statalist@hsphsun2.harvard.edu
> Subject: st: interpretation of impulse response function results
>
> Dear experts,
>
> I have a quick question on the interpretation of the impulse response function created by Stata. For example, under the command "irf", on page 154 in the Time series manual, using the following command
>
> irf graph oirf, impulse(dln_inc) response(dln_consump)
>
> we graph the oirf. I was wondering what the vertical axis stands for?
>
> On page 155, using the command "irf table oirf, irf(order1 order2)
> impulse(dln_inc) response(dln_consump)", we can display the results.
> How do we interpret these numbers? What does ".004934" mean in the context? Is the following explanation correct: Given one standard deviation changes in "dln_inc" in quarter t, there are .004934 standard deviation changes in  "dln_consump" in quarter t? Or both variables are measured in their original units instead of standard deviation?
>
> Thanks! I really appreciate your help!
>
> Best,
> Yunxian
> *
> *   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/
>
> *
> *   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/
>

*
*   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/