GPFDA: GPFDA: A package for Gaussian Process Regression for...

In GPFDA: Gaussian Process for Functional Data Analysis

GPFDA: A package for Gaussian Process Regression for Functional Data Analysis

Description

Gaussian Process Regression for Functional Data Analysis

Details

The main functions of the package are:

gpr

Gaussian process regression using stationary separable covariance kernels.

nsgpr

Gaussian process regression using nonstationary and/or nonseparable covariance kernels.

mgpr

Multivariate Gaussian process – regression for multivariate outputs.

gpfr

Functional regression model given by

y_m(t)=μ_m(t)+τ_m(x)+ε_m(t),

where m is the m-th curve or surface; μ_m is from functional regression; and τ_m is from Gaussian Process regression with mean 0 covariance matrix k(\bf θ).

Author(s)

Jian Qing Shi, Yafeng Cheng, Evandro Konzen

References

Shi, J. Q., and Choi, T. (2011), “Gaussian Process Regression Analysis for Functional Data”, CRC Press.

GPFDA documentation built on May 7, 2022, 5:06 p.m.