propagate {FVDDPpkg}

Propagate the Fleming-Viot latent signal in time

Description

Propagate the Fleming-Viot latent signal in time

Usage

propagate(fvddp, delta.t)

Arguments

fvddp

An instance of class generated via initialize(). In order to perform the propagation, the FVDDP has to be fed some data using update(), at least once.

delta.t

The non-negative time of the propagation. If 0, the returned process is the input.

Value

A list of the same class to the one given as an input (fvddp). The amount of rows of the matrix M, as well as the vector of weights, w, will increase. The hyperparameters will be the same.

References

Papaspiliopoulos O, Ruggiero M, Spanò D (2016). “Conjugacy properties of time-evolving Dirichlet and gamma random measures.” Electronic Journal of Statistics, 10(2), 3452 – 3489. doi:10.1214/16-EJS1194.

See Also

approx.propagate() for a (faster) Monte-Carlo-based analogous.

Examples

FVDDP = initialize(1, function(x) rpois(x, 3),
                   function(x) dpois(x, 3), TRUE)
FVDDP = update(FVDDP, c(4,5))
propagate(FVDDP, 0.2)

FVDDP = initialize(3, function(x) rnorm(x, -1,3),
                   function(x) dnorm(x, -1, 3), FALSE)
FVDDP = update(FVDDP, c(-1.145, 0.553, 0.553, 0.553))
propagate(FVDDP, 0.6)