I need to build a weighted index, given some variables using the VAR (vector auto regression) approach. The weights of the variable are to be decided by a impulse response function.
I need some approach on deciding what all variables to go in the model. I have a pre-selected bunch of variables(based on prior), but how screen them further in building a good model.
Can anyone suggest me papers or approach where optimal selection of variables in VAR is explained.
I will not be using Eviews, so please give me a general approach on how to approach this
For econometric discussions not necessarily related to EViews.
1 post • Page 1 of 1
Who is online
Users browsing this forum: No registered users and 5 guests