Learn R Programming

⚠️There's a newer version (11.0.4.1) of this package.Take me there.

tsDyn (version 0.9-32)

Nonlinear time series models with regime switching

Description

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).

Copy Link

Version

Install

install.packages('tsDyn')

Monthly Downloads

3,076

Version

0.9-32

License

GPL (>= 2)

Maintainer

Antonio Fabio Di Narzo

Last Published

July 13th, 2013

Functions in tsDyn (0.9-32)

Simulation and bootstrap of bivariate VECM/TVECM

VAR representation

extension of the bootstrap replications

Additive nonlinear autoregressive model

US unemployment series used in Caner and Hansen (2001)

Impulse response function

Estimation of Vector error correction model (VECM)

Specification of the threshold search

Test of linearity

Trivariate time series plots

Test of linearity

Plotting methods for SETAR and LSTAR subclasses

Test of unit root against SETAR alternative with

availableModels

Available models

Selection of the cointegrating rank with Information criterion.

Linear AutoRegressive models

autotriples.rgl

Interactive trivariate time series plots

Non-linear time series model, base class definition

Virtua VECM model

Forecasting accuracy measures.

US monthly industrial production from Hansen (1999)

Latex representation of fitted setar models

Test of linear cointegration vs threshold cointegration

sigmoid functions

Threshold Vector Error Correction model (VECM)

Multivariate Threshold Autoregressive model

zeroyld time series

delta test of linearity

Mean Absolute Percent Error

Mean Square Error

No cointegration vs threshold cointegration test

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

Simulation of a multivariate Threshold Autoregressive model (TVAR)

computeGradient

computeGradient

selectHyperParms

Automatic selection of model hyper-parameters

Time series of PPI used as example in Bierens and Martins (2010)

Bivariate time series plots

Extract Log-Likelihood

Simulation and bootstrap of Threshold Autoregressive model

Logistic Smooth Transition AutoRegressive model

Bootstrap a multivariate Threshold Autoregressive (TVAR) model

Locally linear model

Test of unit root against SETAR alternative

NLAR common structure

delta test of conditional independence

predict_rolling

Rolling forecasts

Test of the cointegrating rank

Self Threshold Autoregressive model

Selection of the lag with Information criterion.

Predict method for objects of class nlar, VAR or VECM

Neural Network nonlinear autoregressive model

Extract variable showing regime

Residual variance

Getting started with the tsDyn package

Automatic selection of SETAR hyper-parameters

Extract threshold(s) coefficient

Forecast Error Variance Decomposition

Multivariate linear models: VAR and VECM

Extract Log-Likelihood