mssm-package

This package contains particle filter methods for multivariate observed
outcomes and low dimensional state vectors. The methods are intended to
scale well in the dimension of the observed outcomes. The main function in
the package is the <code><a rd-options="" href="/link/mssm?package=mssm&version=0.1.3" data-mini-rdoc="mssm::mssm">mssm</a></code> function. The package also includes
a method to estimate the parameters using a Laplace approximation.
The README contains an example of the features in the package. See
<a href="https://github.com/boennecd/mssm">https://github.com/boennecd/mssm</a>.
The package is still under development and the API and results of the
methods may change.

Provides methods to perform parameter estimation and
make analysis of multivariate observed outcomes through time which depends
on a latent state variable. All methods scale well in the dimension
of the observed outcomes at each time point. The package contains an
implementation of a Laplace approximation, particle filters like
suggested by Lin, Zhang, Cheng, & Chen (2005)
<doi:10.1198/016214505000000349>, and the gradient and observed information
matrix approximation suggested by Poyiadjis, Doucet, & Singh (2011)
<doi:10.1093/biomet/asq062>.

Benjamin Christoffersen

mssm

Multivariate State Space Models

mssm-package function

This package contains particle filter methods for multivariate observed
outcomes and low dimensional state vectors. The methods are intended to
scale well in the dimension of the observed outcomes. The main function in
the package is the <code><a rd-options='' href='mssm'>mssm</a></code> function. The package also includes
a method to estimate the parameters using a Laplace approximation.
The README contains an example of the features in the package. See
<a href='https://github.com/boennecd/mssm'>https://github.com/boennecd/mssm</a>.
The package is still under development and the API and results of the
methods may change.

mssm-package: Multivariate State Space Models

Description

Arguments