statsmodels.tsa.vector_ar.var_model.VAR

class statsmodels.tsa.vector_ar.var_model.VAR(endog, dates=None, names=None, freq=None)

Fit VAR(p) process and do lag order selection

y_t = A_1 y_{t-1} + \ldots + A_p y_{t-p} + u_t

Parameters :

endog : np.ndarray (structured or homogeneous) or DataFrame

names : array-like

must match number of columns of endog

dates : array-like

must match number of rows of endog

Returns :

.fit() method returns VARResults object :

Notes

References Lutkepohl (2005) New Introduction to Multiple Time Series Analysis

Methods

fit([maxlags, method, ic, trend, verbose])	Fit the VAR model
hessian(params)	The Hessian matrix of the model
information(params)	Fisher information matrix of model
initialize()	Initialize (possibly re-initialize) a Model instance. For
loglike(params)	Log-likelihood of model.
predict(params[, start, end, lags, trend])	Returns in-sample predictions or forecasts
score(params)	Score vector of model.
select_order([maxlags, verbose])	Compute lag order selections based on each of the available information

Attributes

endog_names
exog_names