simulate_priors {abtest}

Simulate from Parameter Priors

Description

Function for simulating from the parameter prior distributions.

Usage

simulate_priors(
  nsamples,
  prior_par = list(mu_psi = 0, sigma_psi = 1, mu_beta = 0, sigma_beta = 1),
  hypothesis = "H1"
)

Arguments

nsamples

number of samples.

prior_par

list with prior parameters. This list needs to contain the following elements: mu_psi (prior mean for the normal prior on the test-relevant log odds ratio), sigma_psi (prior standard deviation for the normal prior on the test-relevant log odds ratio), mu_beta (prior mean for the normal prior on the grand mean of the log odds), sigma_beta (prior standard deviation for the normal prior on the grand mean of the log odds). Each of the elements needs to be a real number (the standard deviations need to be positive). The default are standard normal priors for both the log odds ratio parameter and the grand mean of the log odds parameter.

hypothesis

character specifying whether to sample from a two-sided prior (i.e., "H1"), a one-sided prior with lower truncation point (i.e., "H+"), or a one-sided prior with upper truncation point (i.e., "H-").

Value

a data frame with prior samples for the following quantities (see ?ab_test for a description of the underlying model):

• beta: prior samples for the grand mean of the log odds.

• psi: prior samples for the log odds ratio.

• p1: prior samples for the latent "success" probability in the control group.

• p2: prior samples for the latent "success" probability in the experimental group.

• logor: prior samples for the log odds ratio (identical to psi, only included for easier reference).

• or: prior samples for the odds ratio.

• rrisk: prior samples for the relative risk (i.e., the ratio of the "success" probability in the experimental and the control condition).

• arisk: prior samples for the absolute risk (i.e., the difference of the "success" probability in the experimental and control condition)

.

Author(s)

Quentin F. Gronau

Examples

# prior parameters
prior_par <- list(mu_psi = 0, sigma_psi = 1,
                  mu_beta = 0, sigma_beta = 1)

# obtain prior samples
samples <- simulate_priors(nsamples = 1000, prior_par = prior_par)

# plot, e.g., prior samples for absolute risk
hist(samples$arisk)