Learn R Programming

⚠️There's a newer version (2.1-10) of this package.Take me there.

stepR (version 2.0-4)

Multiscale Change-Point Inference

Description

Allows fitting of step-functions to univariate serial data where neither the number of jumps nor their positions is known by implementing the multiscale regression estimators SMUCE (K. Frick, A. Munk and H. Sieling, 2014) and HSMUCE (F. Pein, H. Sieling and A. Munk, 2017) . In addition, confidence intervals for the change-point locations and bands for the unknown signal can be obtained.

Copy Link

Version

Install

install.packages('stepR')

Monthly Downloads

309

Version

2.0-4

License

GPL-3

Maintainer

Pein Florian

Last Published

November 3rd, 2019

Functions in stepR (2.0-4)

BesselPolynomial

Bessel Polynomials

Compare fit blockwise with ground truth

Bounds based on MRC

Reconstruct filtered piecewise constant functions with noise

Computation of the bounds

Confidence intervals for jumps and confidence bands for step functions

Piecewise constant regression with SMUCE

Robust standard deviation estimate

monteCarloSimulation

Monte Carlo simulation

Neighbouring integers

Critical values

parametricFamily

Parametric families

Values of the MRC statistic for 1,000 observations (all intervals)

Family of distributions

Compute Multiresolution Criterion

Interval systems

Digital filters

Piecewise constant multiscale inference

Forward selection of candidate jumps

Fitted step function

Solution path of step-functions

Multiscale Change-Point Inference

Automatic selection of number of jumps

Jump estimation under restrictions

Continuous time Markov chain

Computation of the multiscale statistic

TRANSIT algorithm for detecting jumps

MRC.asymptotic.dyadic

"Asymptotic" values of the MRC statistic (dyadic intervals)

"Asymptotic" values of the MRC statistic (all intervals)