getSample: Extracts the sample from a bayesianOutput

In BayesianTools: General-Purpose MCMC and SMC Samplers and Tools for Bayesian Statistics

Extracts the sample from a bayesianOutput

Description

Extracts the sample from a bayesianOutput

Usage

getSample(
  sampler,
  parametersOnly = T,
  coda = F,
  start = 1,
  end = NULL,
  thin = 1,
  numSamples = NULL,
  whichParameters = NULL,
  reportDiagnostics = FALSE,
  ...
)

## S3 method for class 'matrix'
getSample(
  sampler,
  parametersOnly = T,
  coda = F,
  start = 1,
  end = NULL,
  thin = "auto",
  numSamples = NULL,
  whichParameters = NULL,
  reportDiagnostics = F,
  ...
)

## S3 method for class 'double'
getSample(
  sampler,
  parametersOnly = T,
  coda = F,
  start = 1,
  end = NULL,
  thin = "auto",
  numSamples = NULL,
  whichParameters = NULL,
  reportDiagnostics = F,
  ...
)

## S3 method for class 'integer'
getSample(
  sampler,
  parametersOnly = T,
  coda = F,
  start = 1,
  end = NULL,
  thin = "auto",
  numSamples = NULL,
  whichParameters = NULL,
  reportDiagnostics = F,
  ...
)

## S3 method for class 'data.frame'
getSample(
  sampler,
  parametersOnly = T,
  coda = F,
  start = 1,
  end = NULL,
  thin = "auto",
  numSamples = NULL,
  whichParameters = NULL,
  reportDiagnostics = F,
  ...
)

## S3 method for class 'list'
getSample(
  sampler,
  parametersOnly = T,
  coda = F,
  start = 1,
  end = NULL,
  thin = "auto",
  numSamples = NULL,
  whichParameters = NULL,
  reportDiagnostics = F,
  ...
)

## S3 method for class 'mcmc'
getSample(
  sampler,
  parametersOnly = T,
  coda = F,
  start = 1,
  end = NULL,
  thin = "auto",
  numSamples = NULL,
  whichParameters = NULL,
  reportDiagnostics = F,
  ...
)

## S3 method for class 'mcmc.list'
getSample(
  sampler,
  parametersOnly = T,
  coda = F,
  start = 1,
  end = NULL,
  thin = "auto",
  numSamples = NULL,
  whichParameters = NULL,
  reportDiagnostics = F,
  ...
)

## S3 method for class 'MCMC'
getSample(
  sampler,
  parametersOnly = T,
  coda = F,
  start = 1,
  end = NULL,
  thin = "auto",
  numSamples = NULL,
  whichParameters = NULL,
  reportDiagnostics = F,
  ...
)

## S3 method for class 'MCMC_refClass'
getSample(
  sampler,
  parametersOnly = T,
  coda = F,
  start = 1,
  end = NULL,
  thin = "auto",
  numSamples = NULL,
  whichParameters = NULL,
  reportDiagnostics = F,
  ...
)

Arguments

sampler	an object of class mcmcSampler, mcmcSamplerList, smcSampler, smcSamplerList, mcmc, mcmc.list, double, numeric
parametersOnly	for a BT output, if F, likelihood, posterior and prior values are also provided in the output
coda	works only for mcmc classes - provides output as a coda object. Note: if mcmcSamplerList contains mcmc samplers such as DE that have several chains, the internal chains will be collapsed. This may not be the desired behavior for all applications.
start	for mcmc samplers start value in the chain. For SMC samplers, start particle
end	for mcmc samplers end value in the chain. For SMC samplers, end particle
thin	thinning parameter. Either an integer determining the thinning intervall (default is 1) or "auto" for automatic thinning.
numSamples	sample size (only used if thin = 1). If you want to use numSamples set thin to 1.
whichParameters	possibility to select parameters by index
reportDiagnostics	logical, determines whether settings should be included in the output
...	further arguments

Details

If thin is greater than the total number of samples in the sampler object the first and the last element (of each chain if a sampler with multiples chains is used) are sampled. If numSamples is greater than the total number of samples all samples are selected. In both cases a warning is displayed.

If thin and numSamples is passed, the function will use the thin argument if it is valid and greater than 1, else numSamples will be used.

Author(s)

Florian Hartig

Tankred Ott

Examples

ll = function(x) sum(dnorm(x, log = TRUE))

setup = createBayesianSetup(ll, lower = c(-10,-10), upper = c(10,10))

settings = list(nrChains = 2, iterations = 1000)
out <- runMCMC(bayesianSetup = setup, sampler = "DEzs", settings = settings)

# population MCMCs divide the interations by the number of internal chains,
# so the end of the 3 chains is 1000/3 = 334
sample <- getSample(out, start = 100, end = 334, thin = 10) 

# sampling with number of samples instead of thinning and
# returning a coda object
sample <- getSample(out, start = 100, numSamples = 60, coda = TRUE)
plot(sample)


# MCMC with a single chain:
settings_2 <- list(nrChains = 1, iterations = 1000)
out_2 <- runMCMC(setup, sampler = "Metropolis", settings = settings_2)
sample_2 <- getSample(out_2, numSamples = 100)

BayesianTools documentation built on Feb. 16, 2023, 8:44 p.m.