crawl (version 1.5)

crwSamplePar: Create a weighted importance sample for posterior predictive track simulation.

Description

The crwSamplePar function uses a fitted model object from crwMLE and a set of prediction times to construct a list from which crwPostIS will draw a sample from either the posterior distribution of the state vectors conditional on fitted parameters or a full posterior draw from an importance sample of the parameters.

Usage

crwSamplePar(object.sim, method = "IS", size = 1000, df = Inf,
  grid.eps = 1, crit = 2.5, scale = 1)

Arguments

object.sim

A simulation object from crwSimulator.

method

Method for obtaining weights for movement parameter samples

size

Size of the parameter importance sample

df

Degrees of freedom for the t approximation to the parameter posterior

grid.eps

Grid size for method="quadrature"

crit

Criterion for deciding "significance" of quadrature points (difference in log-likelihood)

scale

Scale multiplier for the covariance matrix of the t approximation

Value

• List with the following elements:
• x
  Longitude coordinate with NA at prediction times
• y
  Similar to above for latitude
• locType
  Indicates prediction types with a "p" or observation times with an "o"
• P1.y
  Initial state covariance for latitude
• P1.x
  Initial state covariance for longitude
• a1.y
  Initial latitude state
• a1.x
  Initial longitude state
• n.errX
  number of longitude error model parameters
• n.errY
  number of latitude error model parameters
• delta
  vector of time differences
• driftMod
  Logical. indicates random drift model
• stopMod
  Logical. Indicated stop model fitted
• stop.mf
  stop model design matrix
• err.mfX
  Longitude error model design matrix
• err.mfY
  Latitude error model design matrix
• mov.mf
  Movement model design matrix
• fixPar
  Fixed values for parameters in model fitting
• Cmat
  Covaraince matrix for parameter sampling distribution
• Lmat
  Cholesky decomposition of Cmat
• par
  fitted parameter values
• N
  Total number of locations
• loglik
  log likelihood of the fitted model
• Time
  vector of observation times
• coord
  names of coordinate vectors in original data
• Time.name
  Name of the observation times vector in the original data
• thetaSampList
  A list containing a data frame of parameter vectors and their associated probabilities for a resample

Details

The crwSamplePar function uses the information in a crwSimulator object to create a set of weights for importance sample-resampling of parameters in a full posterior sample of parameters and locations using crwPostIS. This function is usually called from crwPostIS. The average user should have no need to call this function directly.

See Also

See demo(northernFurSealDemo) for example.