kfMSD: Kalman marginal smoothing

In ilyaZar/RcppSMCkalman: Kalman Filtering and Backward Simulation via RcppSMC

Kalman marginal smoothing

Description

Performs marginal smoothiong i.e. computation of means and variances for p(x_t|y_{1:T})\forall t=1,\ldots,TT, as described in the corresponding "Marginal smoothing - implemented recursions" subsection of the Details section in kfLGSSM.

Usage

kfMSD(dimX, TT, xtt, Ptt, xtt1, Ptt1, A, Q)

Arguments

dimX	integer giving the dimension of the latent state process
TT	integer giving the length of the time series
xtt	forward filtering means as produced by kfMFPD
Ptt	forward filtering variances as produced by kfMFPD
xtt1	predictive means as produced by kfMFPD (if PDSTORE = TRUE)
Ptt1	predictive variances as produced by kfMFPD (if PDSTORE = TRUE)
A	Parameter (or system) matrix of dimension dimX x dimX.
Q	Error VCM of state process of dimension dimX x dimX.

Value

a named list of two:

• msdEXP: predicitve means x_{t+1|t} (see "Marginal smoothing - implemented recursions" in kfLGSSM)

• msdEXP: predicitve variances P_{t+1|t} (see "Marginal smoothing - implemented recursions" in kfLGSSM)

ilyaZar/RcppSMCkalman documentation built on Oct. 19, 2023, 11 a.m.