Get normal prior hyperparameters for the EffTox model.

Source: R/get_efftox_priors.R

Get normal prior hyperparameters for the EffTox model using the algorithm presented in Thall et al. (2014) that targets a family of priors with a pre-specified effective sample size (ESS).

get_efftox_priors(
  doses = NULL,
  scaled_doses = NULL,
  pi_T,
  ess_T,
  pi_E,
  ess_E,
  num_samples = 10^4,
  seed = 123
)

Arguments

doses

A vector of numbers, the doses under investigation. They should be ordered from lowest to highest and be in consistent units. E.g. to conduct a dose-finding trial of doses 10mg, 20mg and 50mg, use c(10, 20, 50). Specify doses or scaled_doses.
scaled_doses

Optional, vector of numbers, representing the scaled doses under investigation. Thall et al. advocate scaled_doses = log(doses) - mean(log(doses)), and that is what we use here. Specify doses or scaled_doses.
pi_T

Vector of prior expectations of probabilities of toxicity at the doses. Should be congruent to doses or scaled_doses.
ess_T

Numerical, sought total effective sample size for priors on parameters in the toxicity sub-model. Thall et al. (2014) advocate values in (0.3, 1.0) but stress that stress-testing with values outside this range may be necessary.
pi_E

Vector of prior expectations of probabilities of efficacy at the doses. Should be congruent to doses or scaled_doses.
ess_E

Numerical, sought total effective sample size for priors on parameters in the efficacy sub-model. Thall et al. (2014) advocate values in (0.3, 1.0) but stress that stress-testing with values outside this range may be necessary.
num_samples

Number of samples to draw from priors. The default 10^4 seems to be a nice compromise between accuracy and speed. Orders of magnitude larger take a long time to run.
seed

Optional seed. This process involves randomness so seeds are used for repeatable results.

Value

An instance of class efftox_priors.

References

Thall, P., Herrick, R., Nguyen, H., Venier, J., & Norris, J. (2014). Effective sample size for computing prior hyperparameters in Bayesian phase I-II dose-finding. Clinical Trials, 11(6), 657-666. https://doi.org/10.1177/1740774514547397

Examples

if (FALSE) {
# Reproduce the priors calculated in Thall et al. (2014)
p <- get_efftox_priors(
  doses = c(1.0, 2.0, 4.0, 6.6, 10.0),
  pi_T = c(0.02, 0.04, 0.06, 0.08, 0.10), ess_T = 0.9,
  pi_E = c(0.2, 0.4, 0.6, 0.8, 0.9), ess_E = 0.9
)
p
# These are close to the published example. They do not match exactly because
# the process of deriving them is iterative.
}