powered by
Get prior distribution parameters for partially parametric or partially parametric+ models
vtPriorPar(prior.y = NULL, tau = NULL, sdalpha = 10, sdrho = 10, vtheta = NULL)
A VTPRIOR list with
VTPRIOR
TAU:vector of \(\tau\)'s for each level
ABCD:A matrix of 4 columns: \(a_q\), \(b_q\), \(a_\rho\), \({\sigma_\rho}\). Each row represents a dose level.
Historical data for generating prior parameters. It has the same structure as obs.y in vtPost.
obs.y
vtPost
Vector of \(\tau\) values. See visit for details. Can not be NULL if prior.y is NULL.
visit
NULL
prior.y
\(\sigma_\alpha\). See visit for details.
\(\sigma_\rho\).
Additional variance term for eliciting prior parameters from prior.y
The priors are specified as \(q^{(l)} \sim Beta(a_q^{(l)}, b_q^{(l)})\), and \(\log\rho^{(l)} \sim N(0, \sigma_\rho^2)\).
par.prior <- vtPriorPar(tau = c(0.2, 0.4, 0.6), sdalpha = 10);
Run the code above in your browser using DataLab