Defines functions prior_predictor

Documented in prior_predictor

# Sum of Unif and Gaussian random variable is a convolution and
# it can calculate explicitly.

#' @title Predict some estimates of parameter
#' @param d A list of data, which can be passed to the \code{fit_Bayesian_FROC}.
#' @return none
# @export
# @examples
prior_predictor <- function(d=d){
f <- fit_Bayesian_FROC( ite  = 11111,  cha = 1, summary = FALSE, dataList = d)
w <-extract(f)$w
m <-extract(f)$m
v <-extract(f)$v
z2 <-extract(f)$z[,2]
z3 <-extract(f)$z[,3]


mean(   (m-w)/(sqrt(v))-1  )

a <-metadata_srsc_per_image(f@dataList)
hh <-a$hh

graphics::hist(Phi_inv(exp(-a$ff[3] ))/w)
mean(Phi_inv(exp(-a$ff[3] ))/w)
message("\n* This function shows that the model parameter named w can be predictied by
 the data as the following quantities

        Phi_inv(exp(-a$ff[3] ))

 where the ff[3] is the most lower FPF (false positive fraction).

 Similar manner can be avaliable for the other parameters.



Try the BayesianFROC package in your browser

Any scripts or data that you put into this service are public.

BayesianFROC documentation built on Jan. 13, 2021, 5:22 a.m.