transformSSM {KFAS} | R Documentation |
transformSSM
transforms the general multivariate Gaussian state space model
to form suitable for sequential processing.
transformSSM(object, type = c("ldl", "augment"))
object |
State space model object from function |
type |
Option |
As all the functions in KFAS use univariate approach i.e. sequential processing,
the covariance matrix H[t] of the observation equation needs to be
either diagonal or zero matrix. Function transformSSM
performs either
the LDL decomposition of H[t], or augments the state vector with
the disturbances of the observation equation.
In case of a LDL decomposition, the new H[t] contains the diagonal part of the
decomposition, whereas observations y[t] and system matrices Z[t] are
multiplied with the inverse of L[t]. Note that although the state estimates and
their error covariances obtained by Kalman filtering and smoothing are identical with those
obtained from ordinary multivariate filtering, the one-step-ahead errors
v[t] and their variances F[t] do differ. The typical
multivariate versions can be obtained from output of KFS
using mvInnovations
function.
model |
Transformed model. |