question on historical decomposition

[pgg1309]

Thanks a lot @AdaemmerP for this very useful package.

I'm trying to implement historical decomposition using local projections. From the traditional VAR structure it is easy to understand the process having as a starting point the Wold decomposition. I was wondering if you have any idea how to calculate historical decomposition under the local projection framework. Any ideas or reference papers would be welcome. Thanks

[AdaemmerP]

Thanks for your interest in the package. Unfortunately, I am not familiar with the concept of historical decomposition, so I cannot be of much help at this point.

[pgg1309]

Thanks. In a traditional VAR, one can use the Wold theorem https://en.wikipedia.org/wiki/Wold%27s_theorem allows one to re-write all the endogenous variables as a sum of past innovations. Therefore one can look at the time series of each endogenous variable as a sum of past innovations (shocks) for ALL other equations (endogenous variables).

Then it allows one to easily construct 'counterfactuals'. For instance, in a standard monetary VAR (output gap, interest rates, inflation) one could build a counterfactual for the output gap excluding (or assuming zero) shocks to interest rates in a given period.

Given the similarity of the local projections and VAR I though it could be possible to do a similar exercise, but was not sure exactly on how to proceed. Thus my question.

Thanks again for the very useful package. Best