statsmodels.tsa.varma_process.VarmaPoly

class statsmodels.tsa.varma_process.VarmaPoly(ar, ma=None)

Class to keep track of Varma polynomial format

Parameters:

arndarray

The autoregressive lag polynomial array, of shape (nlags, nvarall, nvars).

mandarray, optional

The moving-average lag polynomial array, of shape (malags, nvars, nvars). If None, no moving-average terms are used and an identity matrix is used in their place.

Methods

getisinvertible([a])	Check whether the moving-average lag-polynomial is invertible
getisstationary([a])	Check whether the auto-regressive lag-polynomial is stationary
hstack([a, name])	Stack lagpolynomial horizontally in 2d array
hstackarma_minus1()	Stack ar and lagpolynomial vertically in 2d array
reduceform(apoly)	Convert a structural lag polynomial to reduced form
stacksquare([a, name, orientation])	Stack lagpolynomial vertically in 2d square array with eye
vstack([a, name])	Stack lagpolynomial vertically in 2d array
vstackarma_minus1()	Stack ar and lagpolynomial vertically in 2d array

Examples

ar23 = np.array([[[ 1. , 0. ],

[ 0. , 1. ]],

[[-0.6, 0. ],

[ 0.2, -0.6]],

[[-0.1, 0. ],

[ 0.1, -0.1]]])

ma22 = np.array([[[ 1. , 0. ],

[ 0. , 1. ]],

[[ 0.4, 0. ],

[ 0.2, 0.3]]])

Methods

getisinvertible([a])	Check whether the moving-average lag-polynomial is invertible
getisstationary([a])	Check whether the auto-regressive lag-polynomial is stationary
hstack([a, name])	Stack lagpolynomial horizontally in 2d array
hstackarma_minus1()	Stack ar and lagpolynomial vertically in 2d array
reduceform(apoly)	Convert a structural lag polynomial to reduced form
stacksquare([a, name, orientation])	Stack lagpolynomial vertically in 2d square array with eye
vstack([a, name])	Stack lagpolynomial vertically in 2d array
vstackarma_minus1()	Stack ar and lagpolynomial vertically in 2d array