BayesSIM (version 1.0.0)

as_bsim: Construct a Fitted Model Object from Model Setup and MCMC Output

Description

Create a fitted bsim object by combining a BayesSIM setup object with MCMC samples returned by runMCMC().

Usage

as_bsim(setup, mcmc.out)

Value

An object of class "bsim" containing posterior samples, point estimates, fitted values, and related model information.

Arguments

setup

A BayesSIM setup object, typically the output of a _setup function.

mcmc.out

MCMC output corresponding to the result of a call to runMCMC().

Details

This function is mainly intended for workflows where the model structure and the MCMC sampling are performed separately. It collects the MCMC draws across chains, and returns an object of class "bsim" that can be used with generic functions such as summary(), plot(), and predict().

Examples

# \donttest{
simdata2 <- data.frame(DATA1$X, y = DATA1$y)
models <- BayesSIM_setup(y ~ ., data = simdata2)
Ccompile <- compileModelAndMCMC(models)
nimSampler <- get_sampler(Ccompile)
initList <- getInit(models)
mcmc.out <- runMCMC(nimSampler, niter = 5000, nburnin = 1000, thin = 1,
                   nchains = 1, setSeed = TRUE, inits = initList,
                   summary = TRUE, samplesAsCodaMCMC = TRUE)
fit2 <- as_bsim(models, mcmc.out)
summary(fit2)
# }