A function for testing sample split given subsampled data.
SMPLSplit_het(data,dep,indep,th,trim_per,rep,plot)
LM-test for no threshold.
bootstrap P-Value.
the data in either data.frame or matrix
the name of dependent variable.
the name(s) of independent variable(s).
the name of threshold variable.
trimmed percentage.
number of bootstrap repetition.
=1, plot; =0, do not plot.
This code tests for the presence of threshold. It generalizes the simple code of Dr. Hansen, allowing Heteroskedastic Errors (White Corrected).
Hanse B. E. (2000) Sample Splitting and Threshold Estimation. Econometrica, 68, 575-603.