Convert a discrete probability distribution to a smooth mostly-isotonic function

Convert a discrete probability distribution to a smooth mostly-isotonic function

measure_to_smooth_iso(
  mu,
  n,
  kernel = "normal",
  bandwidth = 0.1,
  tol = .Machine$double.eps * 10
)

Arguments

mu

A named list containing two vectors of the same length, `vals` and `probs`. mu represents a discrete probability distribution.

n

integer number of equidistant points on [min(mu$vals), max(mu$vals)] which will be the support of the returned isotonic function

kernel

the kernel to be used. Can be abbreviated. Type ?ksmooth for details.

bandwidth

the bandwidth. The kernels are scaled so that their quartiles (viewed as probability densities) are at +/- 0.25*bandwidth. Type ?ksmooth for details.

tol

tolerance for shifting cumulative probabilities

Value

Vector representing isotonic function values