Summarize parameter inference and convergence diagnostics.
# S3 method for dreamer_bma
summary(object, ...)a dreamer MCMC object.
additional arguments (which are ignored).
Returns a named list with elements model_weights and summary
containing the prior and posterior weights for each model and inference on parameters for each model as well as MCMC diagnostics.
set.seed(888)
data <- dreamer_data_linear(
n_cohorts = c(20, 20, 20),
dose = c(0, 3, 10),
b1 = 1,
b2 = 3,
sigma = 5
)
# Bayesian model averaging
output <- dreamer_mcmc(
data = data,
n_adapt = 1e3,
n_burn = 1e3,
n_iter = 1e4,
n_chains = 2,
silent = FALSE,
mod_linear = model_linear(
mu_b1 = 0,
sigma_b1 = 1,
mu_b2 = 0,
sigma_b2 = 1,
shape = 1,
rate = .001,
w_prior = 1 / 2
),
mod_quad = model_quad(
mu_b1 = 0,
sigma_b1 = 1,
mu_b2 = 0,
sigma_b2 = 1,
mu_b3 = 0,
sigma_b3 = 1,
shape = 1,
rate = .001,
w_prior = 1 / 2
)
)
#> mod_linear
#> start : 2024-04-01 17:24:47.769
#> Compiling model graph
#> Resolving undeclared variables
#> Allocating nodes
#> Graph information:
#> Observed stochastic nodes: 6
#> Unobserved stochastic nodes: 3
#> Total graph size: 50
#>
#> Initializing model
#>
#> finish: 2024-04-01 17:24:47.833
#> total : 0.06 secs
#> mod_quad
#> start : 2024-04-01 17:24:47.834
#> Compiling model graph
#> Resolving undeclared variables
#> Allocating nodes
#> Graph information:
#> Observed stochastic nodes: 6
#> Unobserved stochastic nodes: 4
#> Total graph size: 59
#>
#> Initializing model
#>
#> finish: 2024-04-01 17:24:47.906
#> total : 0.07 secs
# all models (also show model weights)
summary(output)
#> $model_weights
#> # A tibble: 2 × 3
#> model posterior_weight prior_weight
#> <chr> <chr> <chr>
#> 1 mod_linear 72.1% 50.0%
#> 2 mod_quad 27.9% 50.0%
#>
#> $summary
#> # A tibble: 7 × 14
#> model param mean sd se se_ts `2.5%` `25%` `50%` `75%`
#> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 mod_linear b1 0.562 0.694 0.00490 0.00482 -0.813 0.0950 0.568 1.03
#> 2 mod_linear b2 3.02 0.139 0.000979 0.000979 2.75 2.93 3.02 3.12
#> 3 mod_linear sigma 5.23 0.489 0.00346 0.00350 4.37 4.88 5.18 5.53
#> 4 mod_quad b1 0.612 0.730 0.00516 0.00514 -0.808 0.121 0.602 1.10
#> 5 mod_quad b2 2.87 0.564 0.00398 0.00430 1.74 2.50 2.88 3.26
#> 6 mod_quad b3 0.0156 0.0556 0.000393 0.000425 -0.0905 -0.0223 0.0147 0.0529
#> 7 mod_quad sigma 5.29 0.509 0.00360 0.00398 4.41 4.93 5.25 5.61
#> # ℹ 4 more variables: `97.5%` <dbl>, gelman_point <dbl>, gelman_upper <dbl>,
#> # effective_size <dbl>
#>
# single model
summary(output$mod_linear)
#> # A tibble: 3 × 13
#> param mean sd se se_ts `2.5%` `25%` `50%` `75%` `97.5%`
#> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 b1 0.562 0.694 0.00490 0.00482 -0.813 0.0950 0.568 1.03 1.92
#> 2 b2 3.02 0.139 0.000979 0.000979 2.75 2.93 3.02 3.12 3.29
#> 3 sigma 5.23 0.489 0.00346 0.00350 4.37 4.88 5.18 5.53 6.30
#> # ℹ 3 more variables: gelman_point <dbl>, gelman_upper <dbl>,
#> # effective_size <dbl>