STAR

star

embedding dimension, time delay, forecasting steps

m, d, steps

noRegimes

series

'time delay' for the threshold variable (as multiple of
  embedding time delay d)

thDelay

coefficients for the lagged time series, to obtain the
  threshold variable

thVar

significance level for no. of regimes testing

further arguments to be passed as <code>control</code> list to
  <code><a href="/link/optim?package=tsDyn&version=0.7-23" rd-options="" data-mini-rdoc="tsDyn::optim">optim</a></code>

control

trace

STAR model fitting with automatic number of regimes selection

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 dynamicsis available when the
        transition is either direct (TAR: threshold AR) or smooth
        (STAR: smooth transition AR, LSTAR). For multivariate series,
        estimation and testing of threshold cointegration TVAR/TVECM
        models can be done.

STAR: STAR model

Description

Usage

Arguments

Value

Details

See Also

Examples