statsmodels.tsa.vector_ar.var_model.VARProcess¶
-
class
statsmodels.tsa.vector_ar.var_model.
VARProcess
(coefs, coefs_exog, sigma_u, names=None, _params_info=None)[source]¶ Class represents a known VAR(p) process
- Parameters
- coefs
ndarray
(p
x
k
x
k
) coefficients for lags of endog, part or params reshaped
- coefs_exog
ndarray
parameters for trend and user provided exog
- sigma_u
ndarray
(k
x
k
) residual covariance
- namessequence (
length
k
) - _params_info
dict
internal dict to provide information about the composition of params, specifically k_trend (trend order) and k_exog_user (the number of exog variables provided by the user). If it is None, then coefs_exog are assumed to be for the intercept and trend.
- coefs
Methods
acf
([nlags])Compute theoretical autocovariance function
acorr
([nlags])Autocorrelation function
forecast
(y, steps[, exog_future])Produce linear minimum MSE forecasts for desired number of steps ahead, using prior values y
forecast_cov
(steps)Compute theoretical forecast error variance matrices
forecast_interval
(y, steps[, alpha, exog_future])Construct forecast interval estimates assuming the y are Gaussian
get_eq_index
(name)Return integer position of requested equation name
Long run intercept of stable VAR process
is_stable
([verbose])Determine stability based on model coefficients
Compute long-run effect of unit impulse
ma_rep
([maxn])Compute MA(\(\infty\)) coefficient matrices
mean
()Long run intercept of stable VAR process
mse
(steps)Compute theoretical forecast error variance matrices
orth_ma_rep
([maxn, P])Compute orthogonalized MA coefficient matrices using P matrix such that \(\Sigma_u = PP^\prime\).
plot_acorr
([nlags, linewidth])Plot theoretical autocorrelation function
plotsim
([steps, offset, seed])Plot a simulation from the VAR(p) process for the desired number of steps
simulate_var
([steps, offset, seed])simulate the VAR(p) process for the desired number of steps
to_vecm
()