uTAR.grid: Search for Threshold Value of A Two-Regime SETAR Model

In ConvFuncTimeSeries/test_t: Nonlinear time series analysis

Description

Search for the threshold of a SETAR model for a given range of candidates for threshold values, and perform recursive LS estimation. The program uses a grid to search for threshold value. It is a conservative approach, but might be more reliable than the Li and Tong (2016) procedure.

Usage

uTAR.grid(y, p1, p2, d = 1, thrV = NULL, thrQ = c(0, 1),
  Trim = c(0.1, 0.9), include.mean = T)

Arguments

y	a vector of time series.
p1, p2	AR-orders of regime 1 and regime 2.
d	delay for threshold variable, default is 1.
thrV	threshold variable. if it is not null, thrV must have the same length as that of y.
thrQ	lower and upper limits for the possible threshold values.
Trim	lower and upper trimming to control the sample size in each regime.
include.mean	a logical value for including constant term.

Value

uTAR.grid returns a list with components:

data	the data matrix, y.
arorder	AR orders of regimes 1 and 2.
residuals	estimated innovations.
coefs	a 2-by-(p+1) matrices. The first row show the estimation results in regime 1, and the second row shows these in regime 2.
sigma	estimated innovational covariance matrices of regimes 1 and 2.
nobs	numbers of observations in regimes 1 and 2.
delay	the delay for threshold variable.
model1,model2	estimated models of regimes 1 and 2.
cnst	logical values indicating whether the constant terms are included in regimes 1 and 2.
thr	threshold value.
D	a set of possible threshold values.
RSS	residual sum of squares.
information	information criterion.
sresi	standardized residuals.

References

Li, D., and Tong. H. (2016) Nested sub-sample search algorithm for estimation of threshold models. Statisitca Sinica, 1543-1554.

Examples

arorder=rep(1,2)
ar.coef=matrix(c(0.7,-0.8),2,1)
y=uTAR.sim(100,arorder,ar.coef,1,0)
uTAR.grid(y$series,1,1,1,y$series,c(0,1),c(0.2,0.8),TRUE)

ConvFuncTimeSeries/test_t documentation built on May 29, 2019, 1:39 p.m.