summary.bsim: Summarize `BayesSIM`

Description

Provides a summary for BayesSIM.

Usage

# S3 method for bsim
summary(object, ...)
# S3 method for summary.bsim
print(x, digits = 3, ...)

Value

The function summarizes posterior MCMC samples by reporting key statistics, including:

Posterior mean and median
Empirical standard deviation
95% credible interval (lower and upper quantiles)
Potential scale reduction factor (gelman) for multiple chains
Effective sample size (ESS)

By default, the index vector and error variance are only included in the summary. If variable selection methods are used, such as uniform sphere and spike-and-slab prior, the indicator vector (nu) is also included. Note that the potential scale reduction factor for nu can be reported as NaN or Inf, since the indicator rarely changes during the MCMC run.

If the model is fitted with single chain, both all.chain and chain have identical information.

Arguments

object: A fitted object of BayesSIM or individual model.
...: Further arguments passed.
x: A summary output of BayesSIM or individual model.
digits: The minimum number of significant digits to be printed.

Details

A list of summary statistics for MCMC samples, including data.frame table for the results. Each row corresponds to a model parameter, and columns report the statistics.

Examples

Run this code

# \donttest{
simdata2 <- data.frame(DATA1$X, y = DATA1$y)

# 1. One tool version
fit_one <- BayesSIM(y ~ ., data = simdata2,
                    niter = 5000, nburnin = 1000, nchain = 1)

# Check median index vector estimates with standard errors
coef(fit_one, method = "median", se = TRUE)

# Fitted index values of median prediction
fitted(fit_one, type = "linpred", method = "median")

# Residuals of median prediction
residuals(fit_one, method = "median")

# Summary of the model
summary(fit_one)

# Convergence diagnostics
nimTraceplot(fit_one)

# Goodness of fit
GOF(fit_one)

# Fitted plot
plot(fit_one)

# Prediction with 95% credible interval at new data
newx <- data.frame(X1 = rnorm(10), X2 = rnorm(10), X3 = rnorm(10), X4 = rnorm(10))
pred <- predict(fit_one, newdata = newx, interval = "credible", level = 0.95)
plot(pred)


# 2. Split version
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)

# "fit_split" becomes exactly the same as the class of "fit_one" object and apply generic functions.
fit_split <- as_bsim(models, mcmc.out)

# }