quantile.ewcdf: Quantiles of Weighted Empirical Cumulative Distribution Function

Description

Compute quantiles of a weighted empirical cumulative distribution function.

Usage

# S3 method for ewcdf
quantile(x, probs = seq(0, 1, 0.25),
                 names = TRUE, ...,
                 normalise = TRUE, type=1)

Value

Numeric vector of quantiles, of the same length as probs.

Arguments

x: A weighted empirical cumulative distribution function (object of class "ewcdf", produced by ewcdf) for which the quantiles are desired.
probs: probabilities for which the quantiles are desired. A numeric vector of values between 0 and 1.
names: Logical. If TRUE, the resulting vector of quantiles is annotated with names corresponding to probs.
...: Ignored.
normalise: Logical value indicating whether x should first be normalised so that it ranges between 0 and 1.
type: Integer specifying the type of quantile to be calculated, as explained in quantile.default. Only types 1 and 2 are currently implemented.

Author

Adrian Baddeley Adrian.Baddeley@curtin.edu.au, Rolf Turner r.turner@auckland.ac.nz and Ege Rubak rubak@math.aau.dk and Kevin Ummel.

Details

This is a method for the generic quantile function for the class ewcdf of empirical weighted cumulative distribution functions.

The quantile for a probability p is computed as the right-continuous inverse of the cumulative distribution function x (assuming type=1, the default).

If normalise=TRUE (the default), the weighted cumulative function x is first normalised to have total mass 1 so that it can be interpreted as a cumulative probability distribution function.

Examples

Run this code

  z <- rnorm(50)
  w <- runif(50)
  Fun <- ewcdf(z, w)
  quantile(Fun, c(0.95,0.99))

Run the code above in your browser using DataLab