fChange (version 0.2.1)

change_FF: Change Point Analysis Of Functional Data Without Dimension Reduction (Fully Functional)

Description

This function tests whether there is a significant change in the mean function of the functional data, and it will give an estimate for the location of the change. The procedure is based on the standard L-2 norm and hence does not depend on any dimension reduction technique such as fPCA.

Usage

change_FF(fdobj, M = 1000, h = 0, plot = FALSE, ...)

Arguments

fdobj

A functional data object of class 'fd'

M

Number of monte carlo simulations used to get the critical values. The default value is M=1000

h

The window parameter for the estimation of the long run covariance kernel. The default value is h=0, i.e., it assumes iid data

plot

If TRUE plot of the functional data before and after the estimated change and plot of the estimated change function is given

...

Further arguments to pass

Value

pvalue

Approximate p value for testing whether there is a significant change in the mean function

change

Estimated change location

DataBefore

Data before the estimated change

DataAfter

Data after the estimated change

MeanBefore

Mean function before the estimated change

MeanAfter

Mean function after the estimated change

change_fun

Estimated change function

Details

This function dates and detects changes in the mean function of functional data using a fully functional technique that does not dependent on dimension reduction. For more details, see Aue, Rice, Sonmez (2017+)

References

Aue A., Rice G., Sonmez O. (2017+), Detecting and dating structural breaks in functional data without dimension reduction (https://arxiv.org/pdf/1511.04020.pdf)

See Also

change_fPCA

Examples

# NOT RUN {
# generate functional data
fdata = fun_IID(n=100, nbasis=21)
# insert an artifiical change
data_c = insert_change(fdata, k=21, change_location = 0.5, SNR=1)$fundata
change_FF(data_c)$change



# }