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

stepR (version 1.0-1)

Fitting Step-Functions

Description

Allows to fit step-functions to univariate serial data where neither the number of jumps nor their positions is known.

Copy Link

Version

Install

install.packages('stepR')

Monthly Downloads

253

Version

1.0-1

License

GPL-3

Maintainer

Thomas Hotz

Last Published

March 4th, 2015

Functions in stepR (1.0-1)

MRC.1000

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

bounds

Bounds based on MRC

neighbours

Neighbouring integers

stepcand

Forward selection of candidate jumps

stepsel

Automatic selection of number of jumps

MRC.asymptotic

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

stepR-package

Fit step-functions

jumpint

Confidence intervals for jumps and confidence bands for step functions

contMC

Continuous time Markov chain

MRC.asymptotic.dyadic

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

MRC

Compute Multiresolution Criterion

sdrobnorm

Robust standard deviation estimate

stepblock

Step function

transit

TRANSIT algorithm for detecting jumps

jsmurf

Reconstruct filtered piecewise constant functions with noise

Compare fit blockwise with ground truth

dfilter

Digital filters

family

Family of distributions

steppath

Solution path of step-functions

smuceR

Piecewise constant regression with SMUCE

stepbound

Jump estimation under restrictions