[Pomp-commits] r1009 - pkg/pomp/man

[noreply at r-forge.r-project.org]

Author: kingaa
Date: 2014-09-23 21:23:03 +0200 (Tue, 23 Sep 2014)
New Revision: 1009

Removed:
   pkg/pomp/man/bsmc2.Rd
Log:
- merge bsmc2.Rd with bsmc.Rd

Deleted: pkg/pomp/man/bsmc2.Rd
===================================================================
--- pkg/pomp/man/bsmc2.Rd	2014-09-23 19:22:56 UTC (rev 1008)
+++ pkg/pomp/man/bsmc2.Rd	2014-09-23 19:23:03 UTC (rev 1009)
@@ -1,119 +0,0 @@
-\name{bsmc2}
-\alias{bsmc2}
-\alias{bsmc2-pomp}
-\alias{bsmc2,pomp-method}
-\alias{$,bsmcd.pomp-method}
-\alias{$-bsmcd.pomp}
-\alias{plot,bsmcd.pomp-method}
-\alias{plot-bsmcd.pomp}
-\title{Modified Liu and West Bayesian Particle Filter}
-\description{
-  Generates draws from the posterior distribution for the parameters using a plug-and-play variant of the Liu and West algorithm.
-}
-\usage{
-\S4method{bsmc2}{pomp}(object, params, Np, est, smooth = 0.1,
-     tol = 1e-17, seed = NULL,
-     verbose = getOption("verbose"), max.fail = 0,
-     transform = FALSE, \dots)
-}
-\arguments{
-\item{object}{
-    An object of class \code{pomp} or inheriting class \code{pomp}.
-  }
-  \item{params, Np}{
-    Specifications for the prior distribution of particles.
-    See details below.
-  }
-  \item{est}{
-    Names of the rows of \code{params} that are to be estimated.
-    No updates will be made to the other parameters.
-    If \code{est} is not specified, all parameters for which there is variation in \code{params} will be estimated.
-  }
-  \item{smooth}{
-    Kernel density smoothing parameters.
-    The compensating shrinkage factor will be \code{sqrt(1-smooth^2)}.
-    Thus, \code{smooth=0} means that no noise will be added to parameters.
-    Generally, the value of \code{smooth} should be chosen close to 0 (i.e., \code{shrink~0.1}).
-  }
-  \item{tol}{
-    Particles with log likelihood below \code{tol} are considered to be \dQuote{lost}.
-    A filtering failure occurs when, at some time point, all particles are lost.
-    When all particles are lost, the conditional log likelihood at that time point is set to be \code{log(tol)}.
-  }
-  \item{seed}{
-    optional; an object specifying if and how the random number generator should be initialized (\sQuote{seeded}).
-    If \code{seed} is an integer, it is passed to \code{set.seed} prior to any simulation and is returned as the \dQuote{seed} element of the return list.
-    By default, the state of the random number generator is not changed and the value of \code{.Random.seed} on the call is stored in the \dQuote{seed} element of the return list.
-  }
-  \item{verbose}{
-    logical; if \code{TRUE}, print diagnostic messages.
-  }
-  \item{max.fail}{
-    The maximum number of filtering failures allowed.
-    If the number of filtering failures exceeds this number, execution will terminate with an error.
-  }
-  \item{transform}{
-    logical;
-    if \code{TRUE}, the algorithm operates on the transformed scale.
-  }
-  \item{\dots}{
-    currently ignored.
-  }
-}
-\value{
-  An object of class \dQuote{bsmcd.pomp}.
-  The \dQuote{params} slot of this object will hold the parameter posterior medians.
-  The slots of this class include:
-  \item{post}{
-    A matrix containing draws from the approximate posterior distribution.
-  }
-  \item{prior}{
-    A matrix containing draws from the prior distribution (identical to \code{params} on call).
-  }
-  \item{eff.sample.size}{
-    A vector containing the effective number of particles at each time point.
-  }
-  \item{smooth}{
-    The smoothing parameter used (see above).
-  }
-  \item{seed}{
-    The state of the random number generator at the time \code{bsmc} was called.
-    If the argument \code{seed} was specified, this is a copy;
-    if not, this is the internal state of the random number generator at the time of call.
-  }
-  \item{nfail}{
-    The number of filtering failures encountered.
-  }
-  \item{cond.log.evidence}{
-    A vector containing the conditional log evidence scores at each time point.
-  }
-  \item{log.evidence}{
-    The estimated log evidence.
-  }
-  \item{weights}{
-    The resampling weights for each particle.
-  }
-}
-\details{
-  There are two ways to specify the prior distribution of particles.
-  If \code{params} is unspecified or is a named vector, \code{Np} draws are made from the prior distribution, as specified by \code{\link{rprior}}.
-  Alternatively, \code{params} can be specified as an \code{npars} x \code{Np} matrix (with rownames).
-}
-\author{
-  Michael Lavine (lavine at math dot umass dot edu),
-  Matthew Ferrari (mferrari at psu dot edu),
-  Aaron A. King
-  Edward L. Ionides
-}
-\references{
-  Liu, J. and M. West.
-  Combining Parameter and State Estimation in Simulation-Based Filtering.
-  In A. Doucet, N. de Freitas, and N. J. Gordon, editors,
-  Sequential Monte Carlo Methods in Practice, pages 197-224.
-  Springer, New York, 2001.
-}
-\examples{
-## See the "Introducton to pomp" document for examples.
-}
-\seealso{\link{pomp-class}}
-\keyword{ts}