statsmodels.tsa.statespace.kalman_smoother.SmootherResults.smoothed_state_gain#

SmootherResults.smoothed_state_gain(updates_ix, t=None, start=None, end=None, extend_kwargs=None)[source]#

Cov(tilde alpha_{t}, I) Var(I, I)^{-1}

where I is a vector of forecast errors associated with updates_ix.

Parameters:
updates_ixlist

List of indices (t, i), where t denotes a zero-indexed time location and i denotes a zero-indexed endog variable.

tint, optional

A specific period for which to compute the gain. Cannot be used in combination with start or end.

startint, optional

The start of the interval (inclusive) of gains to compute and return. Cannot be used in combination with the t argument. Default is nobs - 1.

endint, optional

The end of the interval (exclusive) of gains to compute and return. Cannot be used in combination with the t argument. Default is nobs.

extend_kwargsdict, optional

Keyword arguments containing updated state space system matrices for handling out-of-sample computations in time-varying state space models.

Returns:
gainndarray

Array of gain matrices. If the argument t is not provided, then it is shaped (end - start, k_states, len(updates_ix)), while if t is given then the first axis is dropped and the array is shaped (k_states, len(updates_ix)).