TVARResult.fevd#

TVARResult.fevd(horizon=20, *, regime)[source]#

Forecast-error variance decomposition within one regime, held frozen.

Parameters:
  • horizon (int) – Largest lead to return.

  • regime (Literal['lower', 'upper']) – Which regime’s dynamics and covariance to read.

Return type:

NDArray[double]

Returns:

An array of shape (horizon + 1, k, k) whose rows sum to one. Inherits both caveats of irf(): the regime is frozen and the ordering of names is an identifying assumption.