Assessment of coverage of posterior intervals for a given weight and evidence level, using simulated data as input.
Usage
oc_coverage(
m,
se,
true_effect,
weights = seq(0, 1, by = 0.01),
map_prior,
sigma,
n_cores = 1,
eval_strategy = "sequential"
)Arguments
- m
Numerical vector of simulated effect estimates.
- se
Numerical vector of simulated standard errors (
mandseneed to have the same length).- true_effect
Numerical value, representing the true treatment effect (usually the mean of the simulated
m).- weights
Vector of weights of the informative component of the MAP prior (defaults to
seq(0, 1, by = 0.01)).- map_prior
A MAP prior containing information about the trials in the source population, created using
RBesT; a mixture of normal distributions is required.- sigma
Standard deviation of the weakly informative component of the MAP prior, recommended to be the unit-information standard deviation.
- n_cores
Integer value, representing the number of cores to be used (defaults to 1); only applies if
eval_strategyis not "sequential".- eval_strategy
Character variable, representing the evaluation strategy, either "sequential", "multisession", or "multicore" (see documentation of
future::plan, defaults to "sequential").
Examples
set.seed(123)
n_sims <- 5 # small number for exemplary application
sim_dat <- list(
"m" = rnorm(n = n_sims, mean = 1.15, sd = 0.1),
"se" = rnorm(n = n_sims, mean = 1.8, sd = 0.3)
)
results <- oc_coverage(
m = sim_dat[["m"]],
se = sim_dat[["se"]],
true_effect = 1.15,
weights = seq(0, 1, by = 0.01),
map_prior = load_tipmap_data("tipmapPrior.rds"),
sigma = 16.23
)
print(results)
#> oc_types
#> weights cov.50p cov.80p cov.90p cov.95p
#> w=0 1.0 1 1 1
#> w=0.01 1.0 1 1 1
#> w=0.02 1.0 1 1 1
#> w=0.03 1.0 1 1 1
#> w=0.04 1.0 1 1 1
#> w=0.05 1.0 1 1 1
#> w=0.06 1.0 1 1 1
#> w=0.07 1.0 1 1 1
#> w=0.08 1.0 1 1 1
#> w=0.09 1.0 1 1 1
#> w=0.1 1.0 1 1 1
#> w=0.11 1.0 1 1 1
#> w=0.12 1.0 1 1 1
#> w=0.13 1.0 1 1 1
#> w=0.14 1.0 1 1 1
#> w=0.15 1.0 1 1 1
#> w=0.16 1.0 1 1 1
#> w=0.17 1.0 1 1 1
#> w=0.18 1.0 1 1 1
#> w=0.19 1.0 1 1 1
#> w=0.2 1.0 1 1 1
#> w=0.21 1.0 1 1 1
#> w=0.22 1.0 1 1 1
#> w=0.23 1.0 1 1 1
#> w=0.24 1.0 1 1 1
#> w=0.25 1.0 1 1 1
#> w=0.26 1.0 1 1 1
#> w=0.27 1.0 1 1 1
#> w=0.28 1.0 1 1 1
#> w=0.29 1.0 1 1 1
#> w=0.3 1.0 1 1 1
#> w=0.31 1.0 1 1 1
#> w=0.32 1.0 1 1 1
#> w=0.33 1.0 1 1 1
#> w=0.34 1.0 1 1 1
#> w=0.35 1.0 1 1 1
#> w=0.36 1.0 1 1 1
#> w=0.37 1.0 1 1 1
#> w=0.38 1.0 1 1 1
#> w=0.39 1.0 1 1 1
#> w=0.4 1.0 1 1 1
#> w=0.41 1.0 1 1 1
#> w=0.42 1.0 1 1 1
#> w=0.43 1.0 1 1 1
#> w=0.44 1.0 1 1 1
#> w=0.45 1.0 1 1 1
#> w=0.46 1.0 1 1 1
#> w=0.47 1.0 1 1 1
#> w=0.48 1.0 1 1 1
#> w=0.49 1.0 1 1 1
#> w=0.5 1.0 1 1 1
#> w=0.51 1.0 1 1 1
#> w=0.52 1.0 1 1 1
#> w=0.53 1.0 1 1 1
#> w=0.54 1.0 1 1 1
#> w=0.55 1.0 1 1 1
#> w=0.56 1.0 1 1 1
#> w=0.57 1.0 1 1 1
#> w=0.58 1.0 1 1 1
#> w=0.59 1.0 1 1 1
#> w=0.6 1.0 1 1 1
#> w=0.61 1.0 1 1 1
#> w=0.62 1.0 1 1 1
#> w=0.63 1.0 1 1 1
#> w=0.64 1.0 1 1 1
#> w=0.65 1.0 1 1 1
#> w=0.66 1.0 1 1 1
#> w=0.67 1.0 1 1 1
#> w=0.68 1.0 1 1 1
#> w=0.69 1.0 1 1 1
#> w=0.7 1.0 1 1 1
#> w=0.71 1.0 1 1 1
#> w=0.72 1.0 1 1 1
#> w=0.73 1.0 1 1 1
#> w=0.74 1.0 1 1 1
#> w=0.75 1.0 1 1 1
#> w=0.76 1.0 1 1 1
#> w=0.77 1.0 1 1 1
#> w=0.78 1.0 1 1 1
#> w=0.79 1.0 1 1 1
#> w=0.8 1.0 1 1 1
#> w=0.81 1.0 1 1 1
#> w=0.82 1.0 1 1 1
#> w=0.83 1.0 1 1 1
#> w=0.84 1.0 1 1 1
#> w=0.85 0.8 1 1 1
#> w=0.86 0.8 1 1 1
#> w=0.87 0.8 1 1 1
#> w=0.88 0.8 1 1 1
#> w=0.89 0.8 1 1 1
#> w=0.9 0.8 1 1 1
#> w=0.91 0.8 1 1 1
#> w=0.92 0.8 1 1 1
#> w=0.93 0.8 1 1 1
#> w=0.94 0.8 1 1 1
#> w=0.95 0.8 1 1 1
#> w=0.96 0.8 1 1 1
#> w=0.97 0.8 1 1 1
#> w=0.98 0.8 1 1 1
#> w=0.99 0.8 1 1 1
#> w=1 0.8 1 1 1