CODEWITHSUNDEEP
rvar
Cleyton Farias
Cleyton Farias

Reputation: 1

impulse response function in r

I have a doubt about some arguments in irf function in R. Among its arguments, there are cumulative = TRUE (or FALSE) and ortho = TRUE (or FALSE). I read the documentation but I still don't get it. In the documentation says "ortho = if TRUE (the default) the orthogonalised impulse response coefficients are computed (only for objects of class ‘varest’).

So, the question is: What's the difference between orthogonalised impulse response coefficients and cumulated impulse response coefficients?

Upvotes: 0

Views: 8371

Answers (2)

Economist_Ayahuasca
Economist_Ayahuasca

Reputation: 1642

regarding the orthogonalised impulse response coefficients it seems that is the indentification strategy. You use a certain ordering of variables so that the shocks to specific variables are ortogonal to other variables. Check the Cholesky decomposition for example, which is the most popular used (Wikipedia). Regarding the cumulative IRF, you are just adding the effects, so it accumulates. They will never will go back to the steady state but reach a negative or positive value, depending on the effects.

Upvotes: 2

James Picerno
James Picerno

Reputation: 490

The vars package for R has functionality for impulse response function. In particular, see the irf() command. For an example on usage, see my code here:

https://gist.github.com/jpicerno1/97a6df866488c069aa5a

along with the accompanying blog post:

http://www.capitalspectator.com/modeling-what-if-scenarios-with-impulse-response-simulations/

Upvotes: 3

Related Questions