Re: [R] help on vector auto-regressive model

Goodness to fit can be checked on looking at the PACF and/or ACF of estimated residuals. Also you might want to see how valid the normality assumption is on them. Generally joint normality is assumed on the data, so that innovation are multivariate white noise process. Luna Moon wrote: Hi

[R] help on vector auto-regressive model

Hi all, I am asking this for my friend. In VAR models, how do we test the goodness-of-fit of a VAR model? More specifically in R? Moreover, are there assumptions on the joint distribution of the data in the model? Thanks a lot! [[alternative HTML version deleted]]