boot.clus: Bootstrap procedure

In CarolinaEuan/HMClust: HMClust

Bootstrap procedure

Description

Executes a bootstrap test to decide the number of clusters when the HSM method is applied. Returns a p-value and if the test rejects K clusters at a level alpha.

Usage

boot.clus(X,Clust,kg0,alpha=c(.01,.05,.1),nboot=1000,parallel=FALSE,freq=1,par.spectrum=c(100,1/(2*dt)))

Arguments

X	Original time series by column.
Clust	Output from HSM.
kg0	Number of groups under the null hypothesis.
alpha	Level of the test.
nboot	Number of boostrap samples.
parallel	To run in a parallel loop. Library "doParallel" is requiered.
freq	Sampling frequency.
par.spectrum	Parameters for the estimation method: par.spectrum[1]=Bandwidth value, par.spectrum[2]= maximun evaluated frequency.

Author(s)

Carolina Euan.

See Also

HSM

CarolinaEuan/HMClust documentation built on Feb. 18, 2024, 10 p.m.