2
I use GMM and would like, given a group of possible instrumental variables, R provide me the best combination with lags.
For example
modelo GMM x ~ a b c d
VI q y z
R provide, based for example on an information or other criterion, which is the best combination of q (-1 to x), y , z (-1 to ....) resulting from the aforementioned condition.
I use Eviews for that, and the parameters would be similar to that
Equation Specification
Instrument List
Estimation weighting matrix = HAC (Newey-West)
Weight updating = N-step Iterative (number of iterations - for choose)
covariance wieghting matrix = choose between White , HAC, two stages
Linear estimation with 1 weight update
Estimation weighting matrix: HAC (Bartlett kernel, Newey-West fixed
bandwidth = 5.0000)
Standard errors & covariance computed using estimation weighting matrix
Instrument specification: xxxxx(-1 TO -6) yyyyyyyy(-1 TO -9)
Constant added to instrument list
I don’t quite understand your question... what is this
q,yandz? You can put an example of how you set a model like this in R, for fixed q, y and z?– Daniel Falbel
Marcus, good afternoon. q would be a suggested instrumental variable (with lags from -1 to x), y and z would also be instrumental variables. Necessarily my question is: I want to get the model with the best parameter I decide (R2 set, Bic, or other) depending on a group of instrumental variables, and they can be outdated as much as necessary to get this model optimized? It was clear, I’m sorry if I wasn’t enough at the first opportunity.
– white_knight
That’s a question that should be closed.
– Flavio Barros