Summarizing HMC Model Fits

summary method for class hmclearn

# S3 method for hmclearn
summary(
  object,
  burnin = NULL,
  probs = c(0.025, 0.05, 0.25, 0.5, 0.75, 0.95, 0.975),
  ...
)

Arguments

object	an object of class hmclearn, usually a result of a call to mh or hmc
burnin	optional numeric parameter for the number of initial MCMC samples to omit from the summary
probs	quantiles to summarize the posterior distribution
...	additional arguments to pass to quantile

Value

Returns a matrix with posterior quantiles and the posterior scale reduction factor statistic for each parameter.

References

Gelman, A., et. al. (2013) Bayesian Data Analysis. Chapman and Hall/CRC.

Gelman, A. and Rubin, D. (1992) Inference from Iterative Simulation Using Multiple Sequences. Statistical Science 7(4) 457-472.

Examples

# Linear regression example
set.seed(521)
X <- cbind(1, matrix(rnorm(300), ncol=3))
betavals <- c(0.5, -1, 2, -3)
y <- X%*%betavals + rnorm(100, sd=.2)

f1 <- hmc(N = 500,
          theta.init = c(rep(0, 4), 1),
          epsilon = 0.01,
          L = 10,
          logPOSTERIOR = linear_posterior,
          glogPOSTERIOR = g_linear_posterior,
          varnames = c(paste0("beta", 0:3), "log_sigma_sq"),
          param=list(y=y, X=X), parallel=FALSE, chains=1)

summary(f1)
#> Summary of MCMC simulation
#> 
#>                    2.5%         5%        25%        50%        75%        95%
#> beta0         0.3761942  0.4648189  0.5155872  0.5325537  0.5497568  0.5781873
#> beta1        -1.0739748 -1.0488209 -1.0281105 -1.0118904 -0.9965476 -0.9627243
#> beta2         0.9617633  1.8882191  1.9997614  2.0164956  2.0314843  2.0521531
#> beta3        -3.0255286 -3.0154147 -2.9970442 -2.9807522 -2.9646554 -2.8305029
#> log_sigma_sq -3.2893269 -3.2522864 -3.1503169 -3.0392322 -2.9052983 -0.4878351
#>                   97.5%
#> beta0         0.5854330
#> beta1        -0.9602134
#> beta2         2.0591168
#> beta3        -1.8103326
#> log_sigma_sq  1.5343091