Copyright	(c) Dominik Schrempf 2020
License	GPL-3.0-or-later
Maintainer	dominik.schrempf@gmail.com
Stability	unstable
Portability	portable
Safe Haskell	None
Language	Haskell2010

Statistics.Gcm

Description

Creation date: Sat Jun 6 16:36:32 2020.

For general help, please refer to the README distributed with the library.

Synopsis

gcm :: (Real a, Real b, Show a, Vector v a, Show b, Vector v b, Vector v Bool) => v a -> v b -> ([a], [b], [Double])
unsafeGcm :: (Real a, Real b, Show a, Vector v a, Show b, Vector v b) => v a -> v b -> ([a], [b], [Double])

Documentation

gcm :: (Real a, Real b, Show a, Vector v a, Show b, Vector v b, Vector v Bool) => v a -> v b -> ([a], [b], [Double]) Source #

Greatest convex minorant. Uses the Pool Adjacent Violators Algorithm (PAVA). It is required that the predictors are ordered with no ties, and that the lengths of the vectors are equal.

Usage:

 gcm predictors responses = (indices, values, slopes)

unsafeGcm :: (Real a, Real b, Show a, Vector v a, Show b, Vector v b) => v a -> v b -> ([a], [b], [Double]) Source #

See gcm.

Assume that: - the lengths of the provided vectors are equal; - the predictors are ordered.