Package: stepR 2.1-10

stepR: Multiscale Change-Point Inference

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, simulataneous multiscale changepoint estimator, (K. Frick, A. Munk and H. Sieling, 2014) <doi:10.1111/rssb.12047> and HSMUCE, heterogeneous SMUCE, (F. Pein, H. Sieling and A. Munk, 2017) <doi:10.1111/rssb.12202>. In addition, confidence intervals for the change-point locations and bands for the unknown signal can be obtained.

Authors:Pein Florian [aut, cre], Thomas Hotz [aut], Hannes Sieling [aut], Timo Aspelmeier [ctb]

stepR_2.1-10.tar.gz
stepR_2.1-10.zip(r-4.5)stepR_2.1-10.zip(r-4.4)stepR_2.1-10.zip(r-4.3)
stepR_2.1-10.tgz(r-4.4-x86_64)stepR_2.1-10.tgz(r-4.4-arm64)stepR_2.1-10.tgz(r-4.3-x86_64)stepR_2.1-10.tgz(r-4.3-arm64)
stepR_2.1-10.tar.gz(r-4.5-noble)stepR_2.1-10.tar.gz(r-4.4-noble)
stepR_2.1-10.tgz(r-4.4-emscripten)stepR_2.1-10.tgz(r-4.3-emscripten)
stepR.pdf |stepR.html✨
stepR/json (API)

# Install 'stepR' in R:
install.packages('stepR', repos = c('https://florianpein.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Uses libs:
  • openblas– Optimized BLAS
  • c++– GNU Standard C++ Library v3
Datasets:

On CRAN:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

3.84 score 1 stars 58 scripts 356 downloads 3 mentions 45 exports 7 dependencies

Last updated 19 days agofrom:de8f89bd35. Checks:OK: 9. Indexed: yes.

TargetResultDate
Doc / VignettesOKOct 19 2024
R-4.5-win-x86_64OKOct 19 2024
R-4.5-linux-x86_64OKOct 19 2024
R-4.4-win-x86_64OKOct 19 2024
R-4.4-mac-x86_64OKOct 19 2024
R-4.4-mac-aarch64OKOct 19 2024
R-4.3-win-x86_64OKOct 19 2024
R-4.3-mac-x86_64OKOct 19 2024
R-4.3-mac-aarch64OKOct 19 2024

Exports:.testSmallScalesBesselPolynomialboundsbounds.MRCchichi.FFTcompareBlockscomputeBoundscomputeStatconfbandcontMCcritValdfilterjsmurfjumpintkMRC.pvaluekMRC.quantkMRC.simulmonteCarloSimulationMRCMRC.FFTMRC.pvalueMRC.quantMRC.simulMRCoeffMRCoeff.FFTneighbourssdrobnormsmuceRstepblockstepboundstepbound.defaultstepbound.stepcandstepcandstepfitstepFitsteppathsteppath.defaultsteppath.stepcandstepselstepsel.AICstepsel.BICstepsel.MRCthresh.smuceRtransit

Dependencies:digestlowpassFilterR.cacheR.methodsS3R.ooR.utilsRcpp

R package stepR

Rendered fromStepR.Rnwusingknitr::knitron Oct 19 2024.

Last update: 2023-08-18
Started: 2017-05-19

Readme and manuals

Help Manual

Help pageTopics
Multiscale Change-Point InferencestepR-package stepR
Bessel PolynomialsBesselPolynomial
Bounds based on MRCbounds bounds.MRC [.bounds
Compare fit blockwise with ground truthcompareBlocks
Computation of the boundscomputeBounds
Computation of the multiscale statisticcomputeStat
Continuous time Markov chaincontMC
Critical valuescritVal
Digital filtersdfilter print.dfilter
Family of distributionsfamily
Interval systemsintervalSystem intervalsystem
Reconstruct filtered piecewise constant functions with noisejsmurf
Confidence intervals for jumps and confidence bands for step functionsconfband confband.stepfit jumpint jumpint.stepfit lines.confband points.jumpint
Monte Carlo simulationmonteCarloSimulation
Compute Multiresolution Criterionchi chi.FFT kMRC.pvalue kMRC.quant kMRC.simul MRC MRC.FFT MRC.pvalue MRC.quant MRC.simul MRCoeff MRCoeff.FFT
Values of the MRC statistic for 1,000 observations (all intervals)MRC.1000
"Asymptotic" values of the MRC statistic (all intervals)MRC.asymptotic
"Asymptotic" values of the MRC statistic (dyadic intervals)MRC.asymptotic.dyadic
Neighbouring integersneighbors neighbours
Parametric familiesparametricFamily parametricfamily
Penaltiespenalties penalty
Robust standard deviation estimatesdrobnorm
Piecewise constant regression with SMUCEsmuceR thresh.smuceR
Step functionlines.stepblock plot.stepblock print.stepblock stepblock [.stepblock
Jump estimation under restrictionsstepbound stepbound.default stepbound.stepcand
Forward selection of candidate jumpsstepcand
Fitted step functionfitted.stepfit lines.stepfit logLik.stepfit plot.stepfit print.stepfit residuals.stepfit stepfit [.stepfit
Piecewise constant multiscale inferencestepFit
Solution path of step-functionslength.steppath logLik.steppath print.steppath steppath steppath.default steppath.stepcand [[.steppath
Automatic selection of number of jumpsstepsel stepsel.AIC stepsel.BIC stepsel.MRC
Test Small Scales.testSmallScales testSmallScales
TRANSIT algorithm for detecting jumpstransit