Non-Stationary Gaussian Process Regression

A Gaussian process regression using a Gaussian kernel for both one-sample and two-sample cases. Includes non-stationary Gaussian kernel (exponential decay function) and several likelihood ratio tests for differential testing along target points.

The 'nsgp' R package for one-sample and two-sample Gaussian Process regression (GPR)

  • supports non-stationary and stationary Gaussian kernels
  • supports dynamic noise from replicates
  • advanced plotting
  • differential detection methods:
  • posterior concentration test
  • expected MLL test


Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


1.0.5 by Markus Heinonen, 7 years ago

Browse source code at

Authors: Markus Heinonen

Documentation:   PDF Manual  

GPL-2 license

Imports MASS

See at CRAN