robflreg (version 1.3)

get.sf.coeffs: Get the estimated regression coefficient functions for scalar-on-function regression model

Description

This function is used to obtain the estimated regression coefficient functions \(\beta_m(s)\) and the estimated regression coefficients \(\gamma_r\) (if \(X.scl \neq NULL\)) for scalar-on-function regression model (see the description in rob.sf.reg based on output object obtained from rob.sf.reg).

Usage

get.sf.coeffs(object)

Value

A list object with the following components:

gp

A list with length \(M\). The \(m\)-th element of gp is a vector containing the grid points of the \(m\)-th functional predictor \(X_m(s)\).

coefficients

A list with length \(M\). The \(m\)-th element of coefficients is a vector of the estimated values of the coefficient function for the \(m\)-th functional predictor \(X_m(s)\).

scl.coefficients

A vector consisting of the estimated coefficients of the scalar predictor \(X.scl\).

Arguments

object

The output object of rob.sf.reg.

Author

Ufuk Beyaztas and Han Lin Shang

Details

In the estimation of regression coefficient functions, the estimated functional principal components of predictor \(\hat{\Psi}_m(s), 1\le m\le M\) variables and the estimated regression parameter function obtained from the regression model of scalar response on the principal component scores of the functional predictor variables \(\hat{B}\) are used, i.e., \(\hat{\beta}_m(s) = \hat{\Psi}_m^\top(s) \hat{B}\).

Examples

sim.data <- generate.sf.data(n = 400, n.pred = 5, n.gp = 101)
Y <- sim.data$Y
X <- sim.data$X
gp <- rep(list(seq(0, 1, length.out = 101)), 5) # grid points of Xs
model.fit <- rob.sf.reg(Y, X, emodel = "classical", gp = gp)
coefs <- get.sf.coeffs(model.fit)