Run Bayesian estimation of naloxone number under-reporting

Samples from Bayesian model using input from data frame

est_naloxone(
  d,
  psi_vec = c(0.7, 0.2, 0.1),
  max_delays = 3,
  delay_alpha = 2,
  delay_beta = 1,
  priors = the$default_priors,
  run_estimation = TRUE,
  rw_type = 1,
  chains = 4,
  iter = 2000,
  seed = 42,
  adapt_delta = 0.85,
  pars = the$default_outputs,
  include = TRUE,
  ...
)

Arguments

d

data frame with format

regions

unique id for region

times

time in months

Orders

Kits ordered

Reported_Used

Kits reported as used

Reported_Distributed

Kits reported as distributed

region_name

Optional label for region

psi_vec

reporting delay distribution

max_delays

maximum delay from kit ordered to kit distributed

delay_alpha

shape parameter for order to distributed delay distribution

delay_beta

shape parameter for order to distributed delay distribution

priors

list of prior values including their mean (mu) and standard deviation (sigma)

run_estimation

if TRUE will sample from posterior otherwise will sample from prior only

rw_type

1 - random walk of order one. 2 - random walk of order 2.

chains

A positive integer specifying the number of Markov chains. The default is 4.

iter

A positive integer specifying the number of iterations for each chain (including warmup). The default is 2000.

seed

Seed for random number generation

adapt_delta

(double, between 0 and 1, defaults to 0.8)

pars

A vector of character strings specifying parameters of interest. The default is NA indicating all parameters in the model. If include = TRUE, only samples for parameters named in pars are stored in the fitted results. Conversely, if include = FALSE, samples for all parameters except those named in pars are stored in the fitted results.

include

Logical scalar defaulting to TRUE indicating whether to include or exclude the parameters given by the pars argument. If FALSE, only entire multidimensional parameters can be excluded, rather than particular elements of them.

...

other parameters to pass to rstan::sampling

Value

An S4 rstan::stanfit class object containing the fitted model

See also

Other inference: est_naloxone_vec()

Examples

if (FALSE) {
library(rstan)
library(bayesplot)

rstan_options(auto_write = TRUE)
options(mc.cores = parallel::detectCores(logical = FALSE))

d <- generate_model_data()
priors <- list(
  c = list(mu = 0, sigma = 1),
  ct0 = list(mu = 0, sigma = 1),
  zeta = list(mu = 0, sigma = 1),
  mu0 = list(mu = 0, sigma = 1),
  sigma = list(mu = 0, sigma = 1)
  )
fit <- est_naloxone(d, priors = priors, iter = 100, chains = 1)
mcmc_pairs(fit,
  pars = c("sigma", "mu0"),
  off_diag_args = list(size = 1, alpha = 0.5)
)
}