TVAR.LRtest(data, lag = 1, trend = TRUE, series, thDelay = 1:m, mTh = 1,
  thVar, nboot = 10, plot = FALSE, trim = 0.1, test = c("1vs", "2vs3"),
  model = c("TAR", "MTAR"), hpc = c("none", "foreach"), trace = FALSE,
  check = FALSE)
Arguments
data       
multivariate time series

lag       
Number of lags to include in each regime

trend       
whether a trend should be added

series       
name of the series

thDelay       
'time delay' for the threshold variable (as multiple of embedding time delay d) PLEASE NOTE that the notation is currently different to univariate models in tsDyn. The left side variable is taken at time t, and not t+1 as in univariate cases.

mTh       
combination of variables with same lag order for the transition variable. Either a single value (indicating which variable to take) or a combination

thVar       
external transition variable

nboot       
Number of bootstrap replications

plot       
Whether a plot showing the results of the grid search should be printed

trim       
trimming parameter indicating the minimal percentage of observations in each regime

test       
Type of usual and alternative hypothesis. See details

model       
Whether the threshold variable is taken in level (TAR) or difference (MTAR)

hpc       
Possibility to run the bootstrap on parallel core. See details in TVECM.HStest

trace       
should additional infos be printed? (logical)

check       
Possibility to check the function by no sampling: the test value should be the same as in the original data