Conf_int: Confidence Intervals For Change Point Estimator

In fChange: Change Point Analysis in Functional Data

Description

A change point in the mean function of functional data is estimated, and for a user selected level aconfidence interval is computed using the fully functional procedure introduced in Aue, Rice and Sonmez (2017+).

Usage

Conf_int(fdobj, h = 0, kern_type = "BT", alpha = 0.05, ...)

Arguments

fdobj	Functional data object, class of "fd"
h	Bandwidth parameter to estimate the long run covariance operator.
kern_type	Kernel to be used for the estimation of the long run covariance function
alpha	Nominal level used to construct the confidence intervals
...	Further arguments to pass

Value

Lower CI	Lower Confidence Band
Estimate	Estimated change point location
Upper CI	Upper Confidence Band

References

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

See Also

LongRun opt_bandwidth change_FF

Examples

fdata1 = fun_AR(n=100, nbasis=21, order=1, kappa=0.5)
Conf_int(fdata1, h=2)

fChange documentation built on May 2, 2019, 6:43 a.m.