[Pomp-commits] r1105 - pkg/pomp/R pkg/pomp/man pkg/pomp/tests www/content www/vignettes
noreply at r-forge.r-project.org
noreply at r-forge.r-project.org
Fri Feb 27 03:57:37 CET 2015
Author: kingaa
Date: 2015-02-27 03:57:36 +0100 (Fri, 27 Feb 2015)
New Revision: 1105
Added:
pkg/pomp/man/lowlevel.Rd
Removed:
pkg/pomp/man/dmeasure-pomp.Rd
pkg/pomp/man/dprocess-pomp.Rd
pkg/pomp/man/init.state-pomp.Rd
pkg/pomp/man/prior-pomp.Rd
pkg/pomp/man/rmeasure-pomp.Rd
pkg/pomp/man/rprocess-pomp.Rd
pkg/pomp/man/skeleton-pomp.Rd
pkg/pomp/man/trajectory-pomp.Rd
Modified:
pkg/pomp/R/pomp-methods.R
pkg/pomp/man/plugins.Rd
pkg/pomp/man/pomp-methods.Rd
pkg/pomp/man/pomp-package.Rd
pkg/pomp/man/pomp.Rd
pkg/pomp/tests/ou2-kalman.R
pkg/pomp/tests/ou2-kalman.Rout.save
pkg/pomp/tests/rw2.R
pkg/pomp/tests/rw2.Rout.save
pkg/pomp/tests/synlik.R
pkg/pomp/tests/synlik.Rout.save
www/content/refs.htm
www/content/refs.tex
www/vignettes/pomp.bib
Log:
- rework some of the help pages
- deprecate 'data.array'
- update references
Modified: pkg/pomp/R/pomp-methods.R
===================================================================
--- pkg/pomp/R/pomp-methods.R 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/R/pomp-methods.R 2015-02-27 02:57:36 UTC (rev 1105)
@@ -51,8 +51,13 @@
## a simple method to extract the data array
setMethod("obs","pomp",obs.internal)
-setMethod("data.array","pomp",obs.internal)
+setMethod("data.array","pomp",function (object, ...) {
+ warning(sQuote("data.array")," is deprecated and will be removed ",
+ "in a future release. Use ",sQuote("obs")," instead.")
+ obs.internal(object,...)
+})
+
## a simple method to extract the array of states
states.internal <- function (object, vars, ...) {
if (length(object at states)==0) {
Deleted: pkg/pomp/man/dmeasure-pomp.Rd
===================================================================
--- pkg/pomp/man/dmeasure-pomp.Rd 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/man/dmeasure-pomp.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -1,47 +0,0 @@
-\name{dmeasure-pomp}
-\docType{methods}
-\alias{dmeasure}
-\alias{dmeasure,pomp-method}
-\alias{dmeasure-pomp}
-\keyword{internal}
-\title{Evaluate the probability density of observations given underlying states in a partially-observed Markov process}
-\description{
- The method \code{dmeasure} evaluates the probability density of a set of measurements given the state of the system.
- This function is part of the low-level interface to \code{pomp} objects.
- This help page does not give instructions on the implementation of models: see \code{\link{pomp}} for instructions.
-}
-\usage{
-\S4method{dmeasure}{pomp}(object, y, x, times, params, log = FALSE, \dots)
-}
-\arguments{
- \item{object}{an object of class \code{pomp}.}
- \item{y}{
- a rank-2 array containing observations.
- The dimensions of \code{y} are \code{nobs} x \code{ntimes}, where \code{nobs} is the number of observables and \code{ntimes} is the length of \code{times}.
- }
- \item{x}{
- a rank-3 array containing the states of the unobserved process.
- The dimensions of \code{x} are \code{nvars} x \code{nreps} x \code{ntimes}, where \code{nvars} is the number of state variables, \code{nreps} is the number of replicates, and \code{ntimes} is the length of \code{times}.
- }
- \item{times}{
- a numeric vector containing the times at which the observations were made.
- }
- \item{params}{
- a rank-2 array of parameters with columns corresponding to the columns of \code{x}.
- Note that the \code{x} and \code{params} must agree in the number of their columns.
- }
- \item{log}{if TRUE, log probabilities are returned.}
- \item{\dots}{at present, these are ignored.}
-}
-\value{
- Returns a matrix of dimensions \code{nreps} x \code{ntimes}.
- If \code{d} is the returned matrix, \code{d[j,k]} is the likelihood of the observation \code{y[,k]} at time \code{times[k]} given the state \code{x[,j,k]}.
-}
-\details{
- This function is essentially a wrapper around the user-supplied \code{dmeasure} slot of the \code{pomp} object.
- For specifications on writing such a function, see \code{\link{pomp}}.
-}
-\author{Aaron A. King \email{kingaa at umich dot edu}}
-\seealso{\code{\link{pomp-class}}, \code{\link{pomp}}}
-\keyword{models}
-\keyword{ts}
Deleted: pkg/pomp/man/dprocess-pomp.Rd
===================================================================
--- pkg/pomp/man/dprocess-pomp.Rd 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/man/dprocess-pomp.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -1,45 +0,0 @@
-\name{dprocess-pomp}
-\docType{methods}
-\alias{dprocess}
-\alias{dprocess,pomp-method}
-\alias{dprocess-pomp}
-\keyword{internal}
-\title{
- Evaluate the probability density of state transitions in a Markov process
-}
-\description{
- The method \code{dprocess} evaluates the probability density of a set of consecutive state transitions.
- This function is part of the low-level interface to \code{pomp} objects.
- This help page does not give instructions on the implementation of models: see \code{\link{pomp}} for instructions.
-}
-\usage{
-\S4method{dprocess}{pomp}(object, x, times, params, log = FALSE, \dots)
-}
-\arguments{
- \item{object}{an object of class \code{pomp}.}
- \item{x}{
- a rank-3 array containing the states of the unobserved process.
- The dimensions of \code{x} are \code{nvars} x \code{nreps} x \code{ntimes}, where \code{nvars} is the number of state variables, \code{nreps} is the number of replicates, and \code{ntimes} is the length of \code{times}.
- }
- \item{times}{
- a numeric vector containing the times corresponding to the given states.
- }
- \item{params}{
- a rank-2 array of parameters with columns corresponding to the columns of \code{x}.
- Note that the \code{x} and \code{params} must agree in the number of their columns.
- }
- \item{log}{if TRUE, log probabilities are returned.}
- \item{\dots}{at present, these are ignored.}
-}
-\value{
- Returns a matrix of dimensions \code{nreps} x \code{ntimes-1}.
- If \code{d} is the returned matrix, \code{d[j,k]} is the likelihood of the transition from state \code{x[,j,k-1]} at time \code{times[k-1]} to state \code{x[,j,k]} at time \code{times[k]}.
-}
-\details{
- This function is essentially a wrapper around the user-supplied \code{dprocess} slot of the \code{pomp} object.
- For specifications on writing such a function, see \code{\link{pomp}}.
-}
-\author{Aaron A. King \email{kingaa at umich dot edu}}
-\seealso{\code{\link{pomp-class}}, \code{\link{pomp}}}
-\keyword{models}
-\keyword{ts}
Deleted: pkg/pomp/man/init.state-pomp.Rd
===================================================================
--- pkg/pomp/man/init.state-pomp.Rd 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/man/init.state-pomp.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -1,39 +0,0 @@
-\name{init.state-pomp}
-\docType{methods}
-\alias{init.state}
-\alias{init.state,pomp-method}
-\alias{init.state-pomp}
-\keyword{internal}
-\title{Return a matrix of initial conditions given a vector of parameters and an initial time.}
-\description{
- The method \code{init.state} returns a vector of initial conditions for the state process when given a vector of parameters \code{params} and an initial time \code{t0}.
- This function is part of the low-level interface to \code{pomp} objects.
- This help page does not give instructions on the implementation of models: see \code{\link{pomp}} for instructions.
-}
-\usage{
-\S4method{init.state}{pomp}(object, params, t0, \dots)
-}
-\arguments{
- \item{object}{an object of class \code{pomp}.}
- \item{params}{
- a named vector of parameters.
- }
- \item{t0}{the initial time at which initial states are requested.}
- \item{\dots}{at present, these are ignored.}
-}
-\value{
- Returns a matrix of initial states (with rownames).
-}
-\examples{
-pompExample(ou2)
-coef(ou2)
-init.state(ou2)
-
-pompExample(euler.sir)
-coef(euler.sir)
-init.state(euler.sir)
-}
-\author{Aaron A. King \email{kingaa at umich dot edu}}
-\seealso{\code{\link{pomp-class}}}
-\keyword{models}
-\keyword{ts}
Added: pkg/pomp/man/lowlevel.Rd
===================================================================
--- pkg/pomp/man/lowlevel.Rd (rev 0)
+++ pkg/pomp/man/lowlevel.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -0,0 +1,182 @@
+\name{Low-level-interface}
+\docType{methods}
+\alias{pomp low-level interface}
+\alias{rprocess}
+\alias{rprocess,pomp-method}
+\alias{rprocess-pomp}
+\alias{dprocess}
+\alias{dprocess,pomp-method}
+\alias{dprocess-pomp}
+\alias{rmeasure}
+\alias{rmeasure,pomp-method}
+\alias{rmeasure-pomp}
+\alias{dmeasure}
+\alias{dmeasure,pomp-method}
+\alias{dmeasure-pomp}
+\alias{dprior}
+\alias{dprior,pomp-method}
+\alias{dprior-pomp}
+\alias{rprior}
+\alias{rprior,pomp-method}
+\alias{rprior-pomp}
+\alias{init.state}
+\alias{init.state,pomp-method}
+\alias{init.state-pomp}
+\alias{skeleton}
+\alias{skeleton,pomp-method}
+\alias{skeleton-pomp}
+\alias{trajectory}
+\alias{trajectory,pomp-method}
+\alias{trajectory-pomp}
+\title{The low-level interface to pomp objects}
+\description{
+ A \code{pomp} object implements a partially observed Markov process (POMP) model.
+ Basic operations on this model (with shorthand terms) include:
+ \enumerate{
+ \item simulation of the state process given parameters (rprocess)
+ \item evaluation of the likelihood of a given state trajectory given parameters (dprocess)
+ \item simulation of the observation process given the states and parameters (rmeasure)
+ \item evaluation of the likelihood of a set of observations given the states and parameters (dmeasure)
+ \item simulation from the prior probability distribution (rprior)
+ \item evaluation of the prior probability density (dprior)
+ \item simulation from the distribution of initial states, given parameters (init.state)
+ \item evaluation of the deterministic skeleton at a point in state space, given parameters (skeleton)
+ \item computation of a trajetory of the deterministic skeleton given parameters (trajectory)
+ }
+ \pkg{pomp} provides S4 methods that implement each of these basic operations.
+ These operations can be combined to implement computations and statistical inference methods that depend only on a model's POMP structure.
+ For convenience, parameter transformations may also be enclosed in a \code{pomp} object.
+
+ This page documents these elements.
+}
+\usage{
+\S4method{rprocess}{pomp}(object, xstart, times, params, offset = 0, \dots)
+\S4method{dprocess}{pomp}(object, x, times, params, log = FALSE, \dots)
+\S4method{rmeasure}{pomp}(object, x, times, params, \dots)
+\S4method{dmeasure}{pomp}(object, y, x, times, params, log = FALSE, \dots)
+\S4method{dprior}{pomp}(object, params, log = FALSE, \dots)
+\S4method{rprior}{pomp}(object, params, \dots)
+\S4method{init.state}{pomp}(object, params, t0, \dots)
+\S4method{skeleton}{pomp}(object, x, t, params, \dots)
+\S4method{trajectory}{pomp}(object, params, times, t0, as.data.frame = FALSE, \dots)
+}
+\arguments{
+ \item{object}{an object of class \code{pomp}.}
+ \item{xstart}{
+ an \code{nvar} x \code{nrep} matrix containing the starting state of the system.
+ Columns of \code{xstart} correspond to states; rows to components of the state vector.
+ One independent simulation will be performed for each column.
+ Note that in this case, \code{params} must also have \code{nrep} columns.
+ }
+ \item{x}{
+ a rank-3 array containing states of the unobserved process.
+ The dimensions of \code{x} are \code{nvars} x \code{nrep} x \code{ntimes}, where \code{nvars} is the number of state variables, \code{nrep} is the number of replicates, and \code{ntimes} is the length of \code{times}.
+ }
+ \item{y}{
+ a matrix containing observations.
+ The dimensions of \code{y} are \code{nobs} x \code{ntimes}, where \code{nobs} is the number of observables and \code{ntimes} is the length of \code{times}.
+ }
+ \item{times, t}{
+ a numeric vector (length \code{ntimes}) containing times.
+ These must be in non-decreasing order.
+ }
+ \item{params}{
+ a \code{npar} x \code{nrep} matrix of parameters.
+ Each column is an independent parameter set and is paired with the corresponding column of \code{x} or \code{xstart}.
+
+ In the case of \code{init.state}, \code{params} is a named vector of parameters.
+ }
+ \item{offset}{
+ integer;
+ the first \code{offset} times in \code{times} will not be returned.
+ }
+ \item{t0}{the initial time at which initial states are requested.}
+ \item{log}{if TRUE, log probabilities are returned.}
+ \item{as.data.frame}{
+ logical; if \code{TRUE}, return the result as a data-frame.
+ }
+ \item{\dots}{
+ In \code{trajectory}, additional arguments are passed to the ODE integrator (if the skeleton is a vectorfield) and ignored if it is a map.
+ See \code{\link[deSolve]{ode}} for a description of the additional arguments accepted.
+
+ In all other cases, additional arguments are ignored.
+ }
+}
+\section{rprocess: simulating the process model}{
+ \code{rprocess} runs simulations of the the process-model portion of partially-observed Markov process.
+
+ When \code{rprocess} is called, the first entry of \code{times} is taken to be the initial time
+ (i.e., that corresponding to \code{xstart}).
+ Subsequent times are the additional times at which the state of the simulated processes are required.
+
+ \code{rprocess} returns a rank-3 array with rownames.
+ Suppose \code{x} is the array returned.
+ Then \code{dim(x)=c(nvars,nrep,ntimes-offset)}, where \code{nvars} is the number of state variables (=\code{nrow(xstart)}), \code{nrep} is the number of independent realizations simulated (=\code{ncol(xstart)}), and \code{ntimes} is the length of the vector \code{times}.
+ \code{x[,j,k]} is the value of the state process in the \code{j}-th realization at time \code{times[k+offset]}.
+ The rownames of \code{x} must correspond to those of \code{xstart}.
+}
+\section{dprocess: evaluating the probability density of a sequence of state transitions}{
+ \code{dprocess} evaluates the probability density of a set of consecutive state transitions.
+
+ \code{dprocess} returns a matrix of dimensions \code{nrep} x \code{ntimes-1}.
+ If \code{d} is the returned matrix, \code{d[j,k]} is the likelihood of the transition from state \code{x[,j,k-1]} at time \code{times[k-1]} to state \code{x[,j,k]} at time \code{times[k]}.
+}
+\section{rmeasure}{
+ \code{rmeasure} simulate the measurement model given states and parameters.
+
+ \code{rmeasure} returns a rank-3 array of dimensions \code{nobs} x \code{nrep} x \code{ntimes}, where \code{nobs} is the number of observed variables.
+}
+\section{dmeasure}{
+ \code{dmeasure} evaluates the probability density of observations given states.
+
+ \code{dmeasure} returns a matrix of dimensions \code{nreps} x \code{ntimes}.
+ If \code{d} is the returned matrix, \code{d[j,k]} is the likelihood of the observation \code{y[,k]} at time \code{times[k]} given the state \code{x[,j,k]}.
+}
+\section{dprior, rprior}{
+ \code{dprior} evaluates the prior probability density and \code{rprior} simulates from the prior.
+}
+\section{init.state}{
+ \code{init.state} returns an \code{nvar} x \code{nrep} matrix of state-process initial conditions when given an \code{npar} x \code{nrep} matrix of parameters, \code{params}, and an initial time \code{t0}.
+ By default, \code{t0} is the initial time defined when the \code{pomp} object ws constructed.
+}
+\section{skeleton}{
+ The method \code{skeleton} evaluates the deterministic skeleton at a point or points in state space, given parameters.
+ In the case of a discrete-time system, the skeleton is a map.
+ In the case of a continuous-time system, the skeleton is a vectorfield.
+ NB: \code{skeleton} just evaluates the deterministic skeleton;
+ it does not iterate or integrate.
+
+ \code{skeleton} returns an array of dimensions \code{nvar} x \code{nrep} x \code{ntimes}.
+ If \code{f} is the returned matrix, \code{f[i,j,k]} is the i-th component of the deterministic skeleton at time \code{times[k]} given the state \code{x[,j,k]} and parameters \code{params[,j]}.
+}
+\section{trajectory}{
+ \code{trajectory} computes a trajectory of the deterministic skeleton of a Markov process.
+ In the case of a discrete-time system, the deterministic skeleton is a map and a trajectory is obtained by iterating the map.
+ In the case of a continuous-time system, the deterministic skeleton is a vector-field; \code{trajectory} uses the numerical solvers in \pkg{\link[deSolve]{deSolve}} to integrate the vectorfield.
+
+ \code{trajectory} returns an array of dimensions \code{nvar} x \code{nrep} x \code{ntimes}.
+ If \code{x} is the returned matrix, \code{x[i,j,k]} is the i-th component of the state vector at time \code{times[k]} given parameters \code{params[,j]}.
+
+ When the skeleton is a vectorfield, \code{trajectory} integrates it using \code{\link[deSolve]{ode}}.
+ When the skeleton is a map, \code{trajectory} iterates it.
+ By default, time is advanced 1 unit per iteration.
+ The user can change this behavior by specifying the desired timestep using the argument \code{skelmap.delta.t} in the construction of the \code{pomp} object.
+}
+\section{Parameter transformations}{
+ User-defined parameter transformations enclosed in the \code{pomp} object can be accessed via \code{\link{partrans}}.
+}
+\examples{
+pompExample(ricker)
+p <- c(r=42,phi=10,sigma=0.3,N.0=7,e.0=0)
+t <- c(1:10,20,30)
+t0 <- 0
+x0 <- init.state(ricker,params=p,t0=t0)
+x <- rprocess(ricker,xstart=x0,times=c(t0,t),params=p,offset=1)
+y <- rmeasure(ricker,params=p,x=x,times=t)
+ll <- dmeasure(ricker,y=y,x=x,times=t,params=p,log=TRUE)
+f <- skeleton(ricker,x=x,t=t,params=p)
+z <- trajectory(ricker,params=p,times=t,t0=t0)
+}
+\author{Aaron A. King \email{kingaa at umich dot edu}}
+\seealso{\code{\link{pomp}}, \link{pomp methods}}
+\keyword{programming}
Modified: pkg/pomp/man/plugins.Rd
===================================================================
--- pkg/pomp/man/plugins.Rd 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/man/plugins.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -1,11 +1,12 @@
\name{plugins}
\alias{plugins}
+\alias{process model plugins}
\alias{onestep.sim}
\alias{euler.sim}
\alias{discrete.time.sim}
\alias{onestep.dens}
\alias{gillespie.sim}
-\title{Plug-ins for dynamical models based on stochastic Euler algorithms}
+\title{Plug-ins for state-process models}
\description{
Plug-in facilities for implementing discrete-time Markov processes and continuous-time Markov processes using the Euler algorithm.
These can be used in the \code{rprocess} and \code{dprocess} slots of \code{pomp}.
Modified: pkg/pomp/man/pomp-methods.Rd
===================================================================
--- pkg/pomp/man/pomp-methods.Rd 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/man/pomp-methods.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -1,5 +1,6 @@
\name{pomp-methods}
\docType{methods}
+\alias{pomp methods}
\alias{pomp-methods}
\alias{plot,pomp-method}
\alias{plot-pomp}
@@ -47,7 +48,6 @@
\S4method{coef}{pomp}(object, pars, transform = FALSE, \dots)
\S4method{coef}{pomp}(object, pars, transform = FALSE, \dots) <- value
\S4method{obs}{pomp}(object, vars, \dots)
-\S4method{data.array}{pomp}(object, vars, \dots)
\S4method{partrans}{pomp}(object, params, dir = c("forward","inverse"), \dots)
\S4method{plot}{pomp}(x, y, variables, panel = lines,
nc = NULL, yax.flip = FALSE,
@@ -162,7 +162,7 @@
\code{coef(object,pars,transform=TRUE) <- value} first, discards any names the \code{value} may have, sets \code{names(value) <- pars}, and then replaces the elements of \code{object}'s \code{params} slot \code{parameter.transform(value)}.
In this case, if some of the names in \code{pars} do not already name parameters in \code{coef(object,transform=TRUE)}, then they are concatenated.
}
- \item{obs, data.array}{
+ \item{obs}{
These functions are synonymous.
\code{obs(object)} returns the array of observations.
\code{obs(object,vars)} gives just the observations of variables named \code{vars}.
@@ -236,13 +236,7 @@
\author{Aaron A. King \email{kingaa at umich dot edu}}
\seealso{
\code{\link{pomp}},
- \link{pomp-class},
- \code{\link{rprocess}},
- \code{\link{dprocess}},
- \code{\link{rmeasure}},
- \code{\link{dmeasure}},
- \code{\link{init.state}},
- \code{\link[=simulate-pomp]{simulate}}
+ \link{pomp low-level interface}
}
\keyword{models}
\keyword{ts}
Modified: pkg/pomp/man/pomp-package.Rd
===================================================================
--- pkg/pomp/man/pomp-package.Rd 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/man/pomp-package.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -1,20 +1,25 @@
\name{pomp-package}
\docType{package}
\alias{pomp-package}
-\title{Partially-observed Markov processes}
+\alias{pomp package}
+\title{Inference for partially observed Markov processes}
\description{
- The \pkg{pomp} package provides facilities for inference on time series data using partially-observed Markov processes (AKA state-space models or nonlinear stochastic dynamical systems).
+ The \pkg{pomp} package provides facilities for inference on time series data using partially-observed Markov process (POMP) models.
+ These models are also known as state-space models or nonlinear stochastic dynamical systems.
One can use \pkg{pomp} to fit nonlinear, non-Gaussian dynamic models to time-series data.
- The first step in using \pkg{pomp} is to encode one's model and data in an object of class \code{pomp}.
- One does this via a call to \code{\link{pomp}}, which involves specifying the process and measurement components of the model in one or more of a variety of ways.
+ The package is both a set of tools for data analysis and a platform upon which statistical inference methods for POMP models can be implemented.
+}
+\section{Data analysis using \pkg{pomp}}{
+ The first step in using \pkg{pomp} is to encode one's model(s) and data in objects of class \code{pomp}.
+ One does this via a call to \code{\link{pomp}}, which involves specifying the unobserved state process and the measurement process of the model.
Details on this are given in the documentation for the \code{\link{pomp}} function.
- Examples are given in the \href{http://pomp.r-forge.r-project.org/vignettes/intro_to_pomp.pdf}{\dQuote{Introduction to \pkg{pomp}}} document, in the demos (\code{demo(package='pomp')}), and via the \code{\link{pompExample}} function.
+ Examples are given in the vignettes (\code{vignette(package='pomp')}), in the demos (\code{demo(package='pomp')}), and via the \code{\link{pompExample}} function.
\pkg{pomp} version \Sexpr[echo=F,stage=install,results=text]{packageDescription("pomp",fields="Version")} provides algorithms for
\enumerate{
\item simulation of stochastic dynamical systems; see \code{\link[=simulate-pomp]{simulate}}
\item particle filtering (AKA sequential Monte Carlo or sequential importance sampling); see \code{\link{pfilter}}
- \item the iterated filtering method of Ionides et al. (2006, 2011); see \code{\link{mif}}
+ \item the iterated filtering method of Ionides et al. (2006, 2011, 2015); see \code{\link{mif}}
\item the nonlinear forecasting algorithm of Kendall et al. (2005); see \code{\link{nlf}}
\item the particle MCMC approach of Andrieu et al. (2010); see \code{\link{pmcmc}}
\item the probe-matching method of Kendall et al. (1999, 2005); see \code{\link{probe.match}}
@@ -22,19 +27,23 @@
\item synthetic likelihood a la Wood (2010); see \code{\link{probe}}
\item approximate Bayesian computation (Toni et al. 2009); see \code{\link{abc}}
\item the approximate Bayesian sequential Monte Carlo scheme of Liu & West (2001); see \code{\link{bsmc}}
- \item basic trajectory matching; see \code{\link{traj.match}}.
+ \item simple trajectory matching; see \code{\link{traj.match}}.
}
- The package also provides various tools for plotting and extracting information on models and data as well as an API for algorithm development.
- Future support for additional algorithms in envisioned.
+ The package also provides various tools for plotting and extracting information on models and data.
+}
+\section{History}{
Much of the groundwork for \pkg{pomp} was laid by a working group of the National Center for Ecological Analysis and Synthesis (\acronym{NCEAS}), \dQuote{Inference for Mechanistic Models}.
-
+}
+\section{License}{
\pkg{pomp} is provided under the \acronym{GNU} Public License (\acronym{GPL}).
+}
+\section{Comments, bug reports, feature requests}{
Contributions are welcome, as are comments, feature requests, and bug reports.
See the package website \url{http://pomp.r-forge.r-project.org} for more information, access to the package mailing list, links to the authors' websites, references to the literature, and up-to-date versions of the package source and documentation.
}
\section{Classes}{
\pkg{pomp} makes extensive use of S4 classes.
- The basic class, \code{\link{pomp}}, encodes a partially-observed Markov process together with a uni- or multi-variate data set and (possibly) parameters.
+ The basic class, \code{\link{pomp}}, encodes a partially-observed Markov process together with a uni- or multivariate data set and (possibly) parameters.
}
\section{Documentation}{
The \href{http://pomp.r-forge.r-project.org/vignettes/intro_to_pomp.pdf}{\sQuote{Introduction to \pkg{pomp}}} document illustrates the facilities of the package using familiar stochastic processes.
@@ -47,14 +56,14 @@
\author{Aaron A. King \email{kingaa at umich dot edu}}
\seealso{
\code{\link{pomp}},
+ \link{pomp low-level interface},
\code{\link{pfilter}},
\code{\link[=simulate-pomp]{simulate}},
- \code{\link{trajectory}},
\code{\link{mif}},
\code{\link{nlf}},
\code{\link{probe.match}},
\code{\link{traj.match}},
- \code{\link{bsmc}},
+ \code{\link{bsmc2}},
\code{\link{pmcmc}}
}
\keyword{models}
Modified: pkg/pomp/man/pomp.Rd
===================================================================
--- pkg/pomp/man/pomp.Rd 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/man/pomp.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -340,18 +340,9 @@
}
\author{Aaron A. King \email{kingaa at umich dot edu}}
\seealso{
- \link{pomp-methods},
- \link[pomp]{plugins},
- \code{\link[=pomp-methods]{time}},
- \code{\link[=pomp-methods]{time<-}},
- \code{\link[=pomp-methods]{timezero}},
- \code{\link[=pomp-methods]{timezero<-}},
- \code{\link[=pomp-methods]{coef}},
- \code{\link[=pomp-methods]{coef<-}},
- \code{\link[=pomp-methods]{obs}},
- \code{\link[=pomp-methods]{states}},
- \code{\link[=pomp-methods]{window}},
- \code{\link[=pomp-methods]{as.data.frame.pomp}}
+ \link{pomp methods},
+ \link{pomp low-level interface},
+ \link{process model plugins}
}
\keyword{models}
\keyword{ts}
Deleted: pkg/pomp/man/prior-pomp.Rd
===================================================================
--- pkg/pomp/man/prior-pomp.Rd 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/man/prior-pomp.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -1,35 +0,0 @@
-\name{prior-pomp}
-\docType{methods}
-\alias{dprior}
-\alias{dprior,pomp-method}
-\alias{dprior-pomp}
-\alias{rprior}
-\alias{rprior,pomp-method}
-\alias{rprior-pomp}
-\keyword{internal}
-\title{Evaluate or simulate from the prior probability density}
-\description{
- The method \code{dprior} evaluates the prior probability density and \code{rprior} simulates from it.
- This function is part of the low-level interface to \code{pomp} objects.
- This help page does not give instructions on the implementation of models: see \code{\link{pomp}} for instructions.
-}
-\usage{
-\S4method{dprior}{pomp}(object, params, log = FALSE, \dots)
-\S4method{rprior}{pomp}(object, params, \dots)
-}
-\arguments{
- \item{object}{an object of class \code{pomp}.}
- \item{params}{
- a rank-2 array of parameters with columns corresponding to the columns of \code{x}.
- }
- \item{log}{if TRUE, log probabilities are returned.}
- \item{\dots}{at present, these are ignored.}
-}
-\details{
- These functions are essentially wrappers around the user-supplied \code{dprior} and \code{rprior} functions stored in the \code{pomp} object.
- For specifications on writing these functions, see \code{\link{pomp}}.
-}
-\author{Aaron A. King \email{kingaa at umich dot edu}}
-\seealso{\code{\link{pomp}}}
-\keyword{models}
-\keyword{ts}
Deleted: pkg/pomp/man/rmeasure-pomp.Rd
===================================================================
--- pkg/pomp/man/rmeasure-pomp.Rd 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/man/rmeasure-pomp.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -1,42 +0,0 @@
-\name{rmeasure-pomp}
-\docType{methods}
-\alias{rmeasure}
-\alias{rmeasure,pomp-method}
-\alias{rmeasure-pomp}
-\keyword{internal}
-\title{Simulate the measurement model of a partially-observed Markov process}
-\description{
- The method \code{rmeasure} draws from the distribution of measurements given the state of the system.
- This function is part of the low-level interface to \code{pomp} objects.
- This help page does not give instructions on the implementation of models: see \code{\link{pomp}} for instructions.
-}
-\usage{
-\S4method{rmeasure}{pomp}(object, x, times, params, \dots)
-}
-\arguments{
- \item{object}{an object of class \code{pomp}.}
- \item{x}{
- a rank-3 array containing the states of the unobserved process.
- The dimensions of \code{x} are \code{nvars} x \code{nreps} x \code{ntimes}, where \code{nvars} is the number of state variables, \code{nreps} is the number of simulations, and \code{ntimes} is the number of distinct times.
- }
- \item{times}{
- a numerical vector containing the times at which the measurements are to be made.
- }
- \item{params}{
- a rank-2 array (dimensions \code{npars} x \code{nreps}) of parameters with the parameters corresponding to the columns of \code{x}.
- }
- \item{\dots}{
- at present, these are ignored.
- }
-}
-\value{
- Returns a rank-3 array of dimensions \code{nobs} x \code{nreps} x \code{ntimes}, where \code{nobs} is the number of observed variables.
-}
-\details{
- This function is essentially a wrapper around the user-supplied \code{rmeasure} slot of the \code{pomp} object.
- For specifications on writing such a function, see \code{\link{pomp}}.
-}
-\author{Aaron A. King \email{kingaa at umich dot edu}}
-\seealso{\code{\link{pomp-class}}, \code{\link{pomp}}}
-\keyword{models}
-\keyword{ts}
Deleted: pkg/pomp/man/rprocess-pomp.Rd
===================================================================
--- pkg/pomp/man/rprocess-pomp.Rd 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/man/rprocess-pomp.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -1,51 +0,0 @@
-\name{rprocess-pomp}
-\docType{methods}
-\alias{rprocess}
-\alias{rprocess,pomp-method}
-\alias{rprocess-pomp}
-\keyword{internal}
-\title{Simulate the process model of a partially-observed Markov process}
-\description{
- The method \code{rprocess} runs simulations of the the process-model portion of partially-observed Markov process.
- This function is part of the low-level interface to \code{pomp} objects.
- This help page does not give instructions on the implementation of models: see \code{\link{pomp}} for instructions.
-}
-\usage{
-\S4method{rprocess}{pomp}(object, xstart, times, params, offset, \dots)
-}
-\arguments{
- \item{object}{an object of class \code{pomp}.}
- \item{xstart}{
- a rank-2 array containing the starting state of the system.
- Columns of \code{xstart} correspond to states; rows to state variables.
- If there is more than one column of \code{xstart}, multiple independent simulations will be performed, one corresponding to each column.
- Note that in this case, \code{params} must have the same number of columns as \code{xstart}.
- }
- \item{times}{
- a numerical vector containing times.
- The first entry of \code{times} is the initial time (corresponding to \code{xstart}).
- Subsequent times are the additional times at which the state of the simulated processes are required.
- }
- \item{params}{
- a rank-2 array of parameters with the parameters corresponding to the columns of \code{xstart}.
- }
- \item{offset}{
- throw away the first \code{offset} times.
- }
- \item{\dots}{at present, these are ignored.}
-}
-\value{
- \code{rprocess} returns a rank-3 array with rownames.
- Suppose \code{x} is the array returned.
- Then \code{dim(x)=c(nvars,nreps,ntimes-offset)}, where \code{nvars} is the number of state variables (=\code{nrow(xstart)}), \code{nreps} is the number of independent realizations simulated (=\code{ncol(xstart)}), and \code{ntimes} is the length of the vector \code{times}.
- \code{x[,j,k]} is the value of the state process in the \code{j}-th realization at time \code{times[k+offset]}.
- The rownames of \code{x} must correspond to those of \code{xstart}.
-}
-\details{
- This function is essentially a wrapper around the user-supplied \code{rprocess} slot of the \code{pomp} object.
- For specifications on writing such a function, see \code{\link{pomp}}.
-}
-\author{Aaron A. King \email{kingaa at umich dot edu}}
-\seealso{\code{\link{pomp-class}}, \code{\link{pomp}}}
-\keyword{models}
-\keyword{ts}
Deleted: pkg/pomp/man/skeleton-pomp.Rd
===================================================================
--- pkg/pomp/man/skeleton-pomp.Rd 2015-02-26 11:13:49 UTC (rev 1104)
+++ pkg/pomp/man/skeleton-pomp.Rd 2015-02-27 02:57:36 UTC (rev 1105)
@@ -1,48 +0,0 @@
-\name{skeleton-pomp}
-\docType{methods}
-\alias{skeleton}
-\alias{skeleton,pomp-method}
-\alias{skeleton-pomp}
-\keyword{internal}
-\title{Evaluate the deterministic skeleton at the given points in state space.}
-\description{
- The method \code{skeleton} computes the deterministic skeleton.
- In the case of a discrete-time system, this is the one-step map.
- In the case of a continuous-time system, this is the vector-field.
- NB: \code{skeleton} just evaluates the deterministic skeleton;
- it does not iterate or integrate.
- This function is part of the low-level interface to \code{pomp} objects.
[TRUNCATED]
To get the complete diff run:
svnlook diff /svnroot/pomp -r 1105
More information about the pomp-commits
mailing list