statsmodels.tsa.vector_ar.svar_model.SVARResults

class statsmodels.tsa.vector_ar.svar_model.SVARResults(endog, endog_lagged, params, sigma_u, lag_order, A=None, B=None, A_mask=None, B_mask=None, model=None, trend='c', names=None, dates=None)

Estimate VAR(p) process with fixed number of lags

Parameters:

endogndarray

endog_laggedndarray

paramsndarray

sigma_undarray

lag_orderint

Andarray, optional

neqs x neqs array of estimated structural parameters for the A matrix.

Bndarray, optional

neqs x neqs array of estimated structural parameters for the B matrix.

A_maskndarray of bool, optional

neqs x neqs array, True where the corresponding entry of A is an estimated (unknown) parameter.

B_maskndarray of bool, optional

neqs x neqs array, True where the corresponding entry of B is an estimated (unknown) parameter.

modelSVAR, optional

The SVAR model instance used to produce the results.

trend{“n”, “c”, “ct”, “ctt”}, optional

namessequence of str, optional

List of names of the endogenous variables in order of appearance in endog.

datesarray_like, optional

Attributes:

aicfloat

Akaike information criterion

bicfloat

Bayesian a.k.a.

bsendarray

coefsndarray (p x K x K)

Estimated A_i matrices, A_i = coefs[i-1]

cov_params

Estimated variance-covariance of model coefficients

datesarray_like

detomegafloat

df_modelint

Number of estimated parameters per equation, including the

df_residint

Number of observations minus number of estimated parameters

endogndarray

endog_laggedndarray

fittedvaluesndarray

fpefloat

Final Prediction Error (FPE)

interceptndarray

info_criteriadict of str to float

k_arint

Order of VAR process

k_trendint

llffloat

modelSVAR

nameslist of str

variable names

neqsint

Number of variables (equations)

nobsint

n_totobsint

paramsndarray ((Kp + 1) x K)

A_i matrices and intercept in stacked form [int A_1 … A_p]

pvaluesndarray

residndarray

sigma_undarray (K x K)

Estimate of white noise process variance Var[u_t]

sigma_u_mlendarray

stderrndarray

trendorderint or None

tvaluesndarray

Methods

acf([nlags])	Compute theoretical autocovariance function
acorr([nlags])	Autocorrelation function
cov_params()	Estimated variance-covariance of model coefficients
cov_ybar()	Asymptotically consistent estimate of covariance of the sample mean
fevd([periods, var_decomp])	Compute forecast error variance decomposition ("fevd")
forecast(y, steps[, exog_future])	Produce linear minimum MSE forecasts for desired number of steps ahead, using prior values y
forecast_cov([steps, method])	Compute forecast covariance matrices for desired number of steps
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
intercept_longrun()	Long run intercept of stable VAR process
irf([periods, var_order])	Analyze structural impulse responses to shocks in system
irf_errband_mc([orth, repl, steps, signif, ...])	Compute Monte Carlo integrated error bands assuming normally distributed for impulse response functions
irf_resim([orth, repl, steps, rng, burn, cum])	Simulates impulse response function, returning an array of simulations.
is_stable([verbose])	Determine stability based on model coefficients
long_run_effects()	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])	Unavailable for SVAR
plot()	Plot input time series
plot_acorr([nlags, resid, linewidth])	Plot autocorrelation of sample (endog) or residuals
plot_forecast(steps[, alpha, plot_stderr])	Plot forecast
plot_sample_acorr([nlags, linewidth])	Plot sample autocorrelation function
plotsim([steps, offset, rng])	Plot a simulation from the VAR(p) process for the desired number of steps
reorder(order)	Reorder variables for structural specification
resid_acorr([nlags])	Compute sample autocorrelation (including lag 0)
resid_acov([nlags])	Compute centered sample autocovariance (including lag 0)
sample_acorr([nlags])	Compute sample autocorrelation (including lag 0)
sample_acov([nlags])	Compute sample autocovariance (including lag 0)
simulate_var([steps, offset, rng, ...])	Simulate the VAR(p) process for the desired number of steps
sirf_errband_mc([orth, repl, steps, signif, ...])	Compute Monte Carlo integrated error bands assuming normally distributed for impulse response functions
summary()	Compute console output summary of estimates
svar_ma_rep([maxn, P])	Compute Structural MA coefficient matrices using MLE of A, B
test_causality(caused[, causing, kind, signif])	Test Granger causality
test_inst_causality(causing[, signif])	Test for instantaneous causality
test_normality([signif])	Test assumption of normal-distributed errors using Jarque-Bera-style omnibus Chi^2 test.
test_whiteness([nlags, signif, adjusted])	Residual whiteness tests using Portmanteau test
to_vecm()	Convert the VAR(p) representation to a VECM error-correction form

Methods

acf([nlags])	Compute theoretical autocovariance function
acorr([nlags])	Autocorrelation function
cov_params()	Estimated variance-covariance of model coefficients
cov_ybar()	Asymptotically consistent estimate of covariance of the sample mean
fevd([periods, var_decomp])	Compute forecast error variance decomposition ("fevd")
forecast(y, steps[, exog_future])	Produce linear minimum MSE forecasts for desired number of steps ahead, using prior values y
forecast_cov([steps, method])	Compute forecast covariance matrices for desired number of steps
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
intercept_longrun()	Long run intercept of stable VAR process
irf([periods, var_order])	Analyze structural impulse responses to shocks in system
irf_errband_mc([orth, repl, steps, signif, ...])	Compute Monte Carlo integrated error bands assuming normally distributed for impulse response functions
irf_resim([orth, repl, steps, rng, burn, cum])	Simulates impulse response function, returning an array of simulations.
is_stable([verbose])	Determine stability based on model coefficients
long_run_effects()	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])	Unavailable for SVAR
plot()	Plot input time series
plot_acorr([nlags, resid, linewidth])	Plot autocorrelation of sample (endog) or residuals
plot_forecast(steps[, alpha, plot_stderr])	Plot forecast
plot_sample_acorr([nlags, linewidth])	Plot sample autocorrelation function
plotsim([steps, offset, rng])	Plot a simulation from the VAR(p) process for the desired number of steps
reorder(order)	Reorder variables for structural specification
resid_acorr([nlags])	Compute sample autocorrelation (including lag 0)
resid_acov([nlags])	Compute centered sample autocovariance (including lag 0)
sample_acorr([nlags])	Compute sample autocorrelation (including lag 0)
sample_acov([nlags])	Compute sample autocovariance (including lag 0)
simulate_var([steps, offset, rng, ...])	Simulate the VAR(p) process for the desired number of steps
sirf_errband_mc([orth, repl, steps, signif, ...])	Compute Monte Carlo integrated error bands assuming normally distributed for impulse response functions
summary()	Compute console output summary of estimates
svar_ma_rep([maxn, P])	Compute Structural MA coefficient matrices using MLE of A, B
test_causality(caused[, causing, kind, signif])	Test Granger causality
test_inst_causality(causing[, signif])	Test for instantaneous causality
test_normality([signif])	Test assumption of normal-distributed errors using Jarque-Bera-style omnibus Chi^2 test.
test_whiteness([nlags, signif, adjusted])	Residual whiteness tests using Portmanteau test
to_vecm()	Convert the VAR(p) representation to a VECM error-correction form

Properties

aic	Akaike information criterion
bic	Bayesian a.k.a.
bse	Standard errors of coefficients, reshaped to match in size
detomega	Return determinant of white noise covariance with degrees of freedom correction:
df_model	Number of estimated parameters per equation, including the intercept / trends
df_resid	Number of observations minus number of estimated parameters
fittedvalues	The predicted insample values of the response variables of the model
fpe	Final Prediction Error (FPE)
hqic	Hannan-Quinn criterion
info_criteria	information criteria for lagorder selection
llf	Compute VAR(p) loglikelihood
pvalues	Two-sided p-values for model coefficients from Student t-distribution
pvalues_dt()
pvalues_endog_lagged()
resid	Residuals of response variable resulting from estimated coefficients
resid_corr	Centered residual correlation matrix
roots	The roots of the VAR process are the solution to (I - coefs[0]*z - coefs[1]*z**2 .
sigma_u_mle	(Biased) maximum likelihood estimate of noise process covariance
stderr	Standard errors of coefficients, reshaped to match in size
stderr_dt	Stderr_dt
stderr_endog_lagged	Stderr_endog_lagged
tvalues	Compute t-statistics.
tvalues_dt()
tvalues_endog_lagged()