A vector autoregressive model of order 
, denoted 
, is a multivariate time series
model in which each component is a linear function of lagged values of every component.
It has the form
 |
where 
and 
are vectors, the 
are coefficient matrices, and 
is a vector of innovations.
The model is stable, and hence has a causal stationary solution, when the roots of
 |
all lie outside the unit circle. A univariate autoregressive model is the one-component special case.
