multimodelClosed {multimark} | R Documentation |
Multimodel inference for 'multimark' closed population abundance models
Description
This function performs Bayesian multimodel inference for a set of 'multimark' closed population abundance models using the reversible jump Markov chain Monte Carlo (RJMCMC) algorithm proposed by Barker & Link (2013).
Usage
multimodelClosed(
modlist,
modprior = rep(1/length(modlist), length(modlist)),
monparms = "N",
miter = NULL,
mburnin = 0,
mthin = 1,
M1 = NULL,
pbetapropsd = 1,
zppropsd = NULL,
sigppropshape = 6,
sigppropscale = 4,
printlog = FALSE
)
Arguments
modlist |
A list of individual model output lists returned by |
modprior |
Vector of length |
monparms |
Parameters to monitor. Only parameters common to all models can be monitored (e.g., " |
miter |
The number of RJMCMC iterations per chain. If |
mburnin |
Number of burn-in iterations ( |
mthin |
Thinning interval for monitored parameters. |
M1 |
Integer vector indicating the initial model for each chain, where |
pbetapropsd |
Scaler specifying the standard deviation of the Normal(0, pbetapropsd) proposal distribution for " |
zppropsd |
Scaler specifying the standard deviation of the Normal(0, zppropsd) proposal distribution for " |
sigppropshape |
Scaler specifying the shape parameter of the invGamma(shape = sigppropshape, scale = sigppropscale) proposal distribution for |
sigppropscale |
Scaler specifying the scale parameter of the invGamma(shape = sigppropshape, scale = sigppropscale) proposal distribution for |
printlog |
Logical indicating whether to print the progress of chains and any errors to a log file in the working directory. Ignored when |
Details
Note that setting parms="all"
is required when fitting individual multimarkClosed
or markClosed
models to be included in modlist
.
Value
A list containing the following:
rjmcmc |
Reversible jump Markov chain Monte Carlo object of class |
pos.prob |
A list of calculated posterior model probabilities for each chain, including the overall posterior model probabilities across all chains. |
Author(s)
Brett T. McClintock
References
Barker, R. J. and Link. W. A. 2013. Bayesian multimodel inference by RJMCMC: a Gibbs sampling approach. The American Statistician 67: 150-156.
See Also
multimarkClosed
, markClosed
, processdata
Examples
# This example is excluded from testing to reduce package check time
# Example uses unrealistically low values for nchain, iter, and burnin
#Generate object of class "multimarksetup"
setup <- processdata(bobcat)
#Run single chain using the default model for bobcat data. Note parms="all".
bobcat.dot <- multimarkClosed(mms=setup,parms="all",iter=1000,adapt=500,burnin=500)
#Run single chain for bobcat data with time effects. Note parms="all".
bobcat.time <- multimarkClosed(mms=setup,mod.p=~time,parms="all",iter=1000,adapt=500,burnin=500)
#Perform RJMCMC using defaults
modlist <- list(mod1=bobcat.dot,mod2=bobcat.time)
bobcat.M <- multimodelClosed(modlist=modlist,monparms=c("N","p"))
#Posterior model probabilities
bobcat.M$pos.prob
#multimodel posterior summary for abundance
summary(bobcat.M$rjmcmc[,"N"])