pfNonlinBS: Nonlinear Bootstrap Particle Filter (Univariate Non-Linear...
In RcppSMC: Rcpp bindings for Sequential Monte Carlo

Description Usage Arguments Details Value Author(s) References Examples

View source: R/pfNonlinBS.R

The pfNonlinBS function provides a simple example for RcppSMC. It is a simple “bootstrap” particle filter which employs multinomial resampling after each iteration applied to the ubiquitous "nonlinear state space model" following Gordon, Salmond and Smith (1993).

The simNonlin function simulates data from the associated model.

1 2	pfNonlinBS(data, particles=500, plot=FALSE) simNonlin(len)

`data`	A vector variable containing the sequence of observations.
`particles`	An integer specifying the number of particles.
`plot`	A boolean variable describing whether a plot should illustrate the (posterior mean) estimated path along with one and two standard deviation intervals.
`len`	The length of data sequence to simulate.

The pfNonlinbs function provides a simple example for RcppSMC. It is based on a simple nonlinear state space model in which the state evolution and observation equations are: x(n) = 0.5 x(n-1) + 25 x(n-1) / (1+x(n-1)^2) + 8 cos(1.2(n-1))+ e(n) and y(n) = x(n)^2 / 20 + f(n) where e(n) and f(n) are mutually-independent normal random variables of variances 10.0 and 1.0, respectively. A boostrap proposal (i.e. sampling from the state equation) is used, together with multinomial resampling after each iteration.

The simNonlin function simulates from the same model.

The pfNonlinBS function returns two vectors, the first containing the posterior filtering means; the second the posterior filtering standard deviations.

The simNonlin function returns a list containing the state and data sequences.

Adam M. Johansen and Dirk Eddelbuettel

N. J. Gordon, S. J. Salmond, and A. F. M. Smith. Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proceedings-F, 140(2):107-113, April 1993.