est_trial_prob: Calculate trial probabilities (posterior and predictive)

In jatotterdell/optimum: Package containing functions and scripts used for optimum study simulations

Description

Calculate trial probabilities (posterior and predictive)

Usage

est_trial_prob(d, ppos_q = 0.95, ppos_sim = 1000,
  post_method = "approx", a1 = 1, b1 = 1, a2 = 1, b2 = 1)

Arguments

d	The Trial data
ppos_q	The vector of cut-points to consider
ppos_sim	Number of simulations from posterior predictive to use in PPoS(q) calculation
post_method	Method used to calculate P(X > Y + delta), one of 'exact' (integration), 'approx' (normal), 'sim' (monte carlo)
a1	Prior shape for treatment 1
b1	Prior scale for treatment 1
a2	Prior shape for treatment 2
b2	Prior scale for treatment 2

Value

Updates 'd' inplace but also returns the updated 'd'. 'post' - current posterior probability, 'post_int' - posterior probability when follow-up enrolled individuals, 'post_fin' - posterior probability when follow-up to maximum sample size, 'ppos_intq' - predictive probability of success given q if follow-up enrolled individuals, 'ppos_finq' - predictive probability of success given q if follow-up to maximum sample size,

jatotterdell/optimum documentation built on May 29, 2019, 1:24 p.m.