tsDyn11.0.4.1 package

Nonlinear Time Series Models with Regime Switching

aar

Additive nonlinear autoregressive model

accuracy_stat

Forecasting accuracy measures.

addRegime

addRegime test

ar_mean

Long-term mean of an AR(p) process

autopairs

Bivariate time series plots

autotriples

Trivariate time series plots

autotriples.rgl

Interactive trivariate time series plots

availableModels

Available models

BBCTest

Test of unit root against SETAR alternative

charac_root

Characteristic roots of the AR coefficients

coefB

Extract cointegration parameters A, B and PI

computeGradient

computeGradient

DataUsUnemp

US unemployment series used in Caner and Hansen (2001)

delta.lin

delta test of linearity

delta

delta test of conditional independence

fevd.nlVar

Forecast Error Variance Decomposition

fitted.nlVar

fitted method for objects of class nlVar, i.e. VAR and VECM models.

getTh

Extract threshold(s) coefficient

GIRF

Generalized Impulse response Function (GIRF)

irf.nlVar

Impulse response function

isLinear

isLinear

KapShinTest

Test of unit root against SETAR alternative with

lags.select

Selection of the lag with Information criterion.

linear

Linear AutoRegressive models

lineVar

Multivariate linear models: VAR and VECM

llar

Locally linear model

logLik.nlVar

Extract Log-Likelihood

lstar

Logistic Smooth Transition AutoRegressive model

MakeThSpec

Specification of the threshold search

MAPE

Mean Absolute Percent Error

mse

Mean Square Error

nlar-methods

NLAR methods

nlar

Non-linear time series model, base class definition

nlar.struct

NLAR common structure

nnet

Neural Network nonlinear autoregressive model

oneStep

oneStep

plot-methods

Plotting methods for SETAR and LSTAR subclasses

plot_ECT

Plot the Error Correct Term (ECT) response

predict.nlar

Predict method for objects of class ‘nlar’ .

predict.VAR

Predict method for objects of class ‘VAR’ , ‘VECM’ or ‘TVAR’

predict_rolling

Rolling forecasts

rank.select

Selection of the cointegrating rank with Information criterion.

rank.test

Test of the cointegrating rank

reexports

Objects exported from other packages

regime

Extract a variable showing the regime

resample_vec

Resampling schemes

resVar

Residual variance

selectHyperParms

Automatic selection of model hyper-parameters

selectSETAR

Automatic selection of SETAR hyper-parameters

setar

Self Threshold Autoregressive model

setar.sim

Simulation and bootstrap of Threshold Autoregressive model (SETAR)

setarTest

Test of linearity against threshold (SETAR)

sigmoid

sigmoid functions

star

STAR model

toLatex.setar

Latex representation of fitted setar models

tsDyn-package

Getting started with the tsDyn package

TVAR.LRtest

Test of linearity

TVAR

Multivariate Threshold Vector Autoregressive model

TVAR.sim

Simulation of a multivariate Threshold Autoregressive model (TVAR)

TVECM.HStest

Test of linear cointegration vs threshold cointegration

TVECM

Threshold Vector Error Correction model (VECM)

TVECM.SeoTest

No cointegration vs threshold cointegration test

TVECM.sim

Simulation and bootstrap a VECM or bivariate TVECM

VAR.boot

Simulate or bootstrap a VAR model

VARrep

VAR representation

VECM

Estimation of Vector error correction model (VECM)

VECM_symbolic

Virtual VECM model

Implements nonlinear autoregressive (AR) time series models. For univariate series, a non-parametric approach is available through additive nonlinear AR. Parametric modeling and testing for regime switching dynamics is available when the transition is either direct (TAR: threshold AR) or smooth (STAR: smooth transition AR, LSTAR). For multivariate series, one can estimate a range of TVAR or threshold cointegration TVECM models with two or three regimes. Tests can be conducted for TVAR as well as for TVECM (Hansen and Seo 2002 and Seo 2006).

  • Maintainer: Matthieu Stigler
  • License: GPL (>= 2)
  • Last published: 2024-02-01