Learn R Programming

qch (version 2.1.0)

FastKerFdr_unsigned: FastKerFdr unsigned

Description

Kernel estimation of the density in a two-components mixture model where one component are a standard Gaussian density. Here we suppose that the density to estimate lives in \(R^+\).

Usage

FastKerFdr_unsigned(
  X,
  p0 = NULL,
  plotting = FALSE,
  NbKnot = 1e+05,
  tol = 1e-05,
  max_iter = 10000
)

Value

A list with the following elements:

p0vector of the estimated proportions of \(H_0\) hypotheses for each of p-value serie.
tauthe vector of \(H_1\) posteriors.
f1a numeric vector, each coordinate \(i\) corresponding to the evaluation of the \(H_1\) density at point \(x_i\), where \(x_i\) is the \(i\)th item in X.
F1a numeric vector, each coordinate \(i\) corresponding to the evaluation of the \(H_1\) cdf at point \(x_i\), where \(x_i\) is the \(i\)th item in X.

Arguments

X

a vector of probit-transformed p-values (corresponding to a p-value serie)

p0

a priori proportion of \(H_0\) hypotheses

plotting

boolean, should some diagnostic graphs be plotted. (Default is FALSE.)

NbKnot

The (maximum) number of knot for the kde procedure. (Default is 1e5.)

tol

a tolerance value for convergence. (Default is 1e-5.)

max_iter

the maximum number of iterations allowed for the algorithm to converge or complete its process.(Default is 1e4.)