getcoef.sigcom: Get the estimated intercept and coefficient functions for linear function-on-function models

Description

This function is used to calculate the estimates for \(\mu(t), \alpha(t), \beta_i(s,t)\) based on the object obtained from cv.sigcom.

Usage

getcoef.sigcom(fit.obj, t.x.coef=NULL, t.y.coef=NULL)

Arguments

fit.obj

the object obtained from cv.sigcom.

t.x.coef

a list of length \(p\) of vectors providing the observation time points of predictors on which coefficient functions will be evaluated. If t.x.coef=NULL (default), t.x in cv.sigcom will be used.

t.y.coef

a vector of observation time points of response function on which the coefficient functions will be evaluated. If t.y.coef=NULL (default), t.y in cv.sigcom will be used.

Value

a list containing

the vector of the estimated values of \(\mu(t)\) at the grid of observation points of the response function (\(t.y.coef\) for cv.sigcom).

beta

a list of length \(p\), the number of functional predictors. Its \(i\)-th component is a matrix of the estimated values of coefficient functions \(\beta_i(s,t)\) of functional predictors at the full grid of observaion time points created by arguments t.x.coef[[i]] and t.y for cv.sigcom. The columns correspond to different observation points for response varible (\(t.y.coef\)).

References

Ruiyan Luo and Xin Qi, (2017) Function-on-Function Linear Regression by Signal Compression, Journal of the American Statistical Association. http://www.tandfonline.com/doi/abs/10.1080/01621459.2016.1164053

Examples

Run this code

# NOT RUN {
#See the examples in cv.sigcom().
# }