Resample_MDR: Perform Monte Carlo simulation of MDR statistic

In gilles-guillot/MDR: Test Loewe additivity with Model Deviation Ratio

Description

Perform Monte Carlo simulation of MDR statistic under generative model and experimental designed known/assumed for the data

Usage

Resample_MDR(
  x,
  y,
  z = NULL,
  n,
  SCDR_model = "Hill2",
  par_Hill = NULL,
  design,
  lower = c(1e-04, 1e-04, 1e-04, 1e-04),
  upper = c(10, 10, 1, 1),
  n_resamp,
  distribution = "binom",
  verbose = TRUE
)

Arguments

x	sequence of doses first compound
y	sequence of doses second compound
z	sequence of responses
n	number of binomial samples at various dose values
SCDR_model	family of the single compound dose-response curve
par_Hill	parameters of the Hill functions. With par_Hill = (a1,b1,a2,b2) a1: a in 1/(1+(a/x)**b) for first compound b1: b in 1/(1+(a/x)**b) for first compound a2: a in 1/(1+(a/x)**b) for second compound b2: b in 1/(1+(a/x)**b) for second compound
design	any of the below 'single-parallel': single ray parallel to an axis (dose of one of the two compounds is fixed), single compound experiment data not used, 'single-ray': single ray design (ratio of doses of two compounds is fixed), single compound experiment data not used 'general' (TODO): fully arbitrary design, all data used including single compound experiment data
lower	lower limits for the search of parameter
upper	upper limits for the search of parameter
n_resamp	number of dataset resampled
distribution	distribution of response conditional on Hill function value
verbose	will print the percentage of computation carried out if TRUE

Details

Input data should include design (x,y,n) AND EITHER vector of response mortality values z OR estimate of dose repose curves parameters par_Hill

Value

a list with an element named MDR_resamp

gilles-guillot/MDR documentation built on Jan. 21, 2020, 8:09 a.m.