[R] [Vars] package: impulse response function

[Jeff Newmiller]

Read the posting guide. We have no way to know what you are doing unless you show the list readers with sample data and code.

If you are wondering about Vector Autoregressive models, I don't claim any specific experience with them, but [1] says they are linear, and I do know that linear models respond in proportion to the magnitude of the input so you don't learn anything useful by changing the magnitude of the input.

I have used the Kronecker delta (impulse) function before, and I have never heard of anyone trying to ascribe a standard deviation to it... only impulse magnitude.

[1] http://en.m.wikipedia.org/wiki/Vector_autoregression
---------------------------------------------------------------------------
Jeff Newmiller                        The     .....       .....  Go Live...
DCN:<jdnewmil at dcn.davis.ca.us>        Basics: ##.#.       ##.#.  Live Go...
                                      Live:   OO#.. Dead: OO#..  Playing
Research Engineer (Solar/Batteries            O.O#.       #.O#.  with
/Software/Embedded Controllers)               .OO#.       .OO#.  rocks...1k
--------------------------------------------------------------------------- 
Sent from my phone. Please excuse my brevity.

Maria Grigoryeva <mm.grigoryeva at gmail.com> wrote:

>Hello,
>
>I'm doing a research on the impulse responses in VAR models and I'm
>having
>troubles in interpretation of R results.
>My question is what is the shock of impulse variable that is produced
>to
>obtain the response? Is it one-standard-deviation positive shock? If it
>is
>so how can I obtain  the responses on other types of shocks, say, 10%
>negative shock?
>
>Thanks a lot,
>
>Marion
>
>	[[alternative HTML version deleted]]
>
>______________________________________________
>R-help at r-project.org mailing list
>https://stat.ethz.ch/mailman/listinfo/r-help
>PLEASE do read the posting guide
>http://www.R-project.org/posting-guide.html
>and provide commented, minimal, self-contained, reproducible code.