For the latest version of JMP Help, visit JMP.com/help.


Publication date: 04/21/2023

Statistical Details for the Model Fit

The model parameters of a Gaussian Process model are fit via maximum likelihood. The fitted parameters are provided in the platform report. These are the parameters:

μ is the Gaussian Process mean,

σ2 is the Gaussian Process variance,

Theta corresponds to the values of θk in the definition of R.

The off-diagonals of the categorical input correlation matrices correspond to the values of τpij in the definition of R.

Note: If your report contains the note Nugget parameters set to avoid singular variance matrix, JMP has added a ridge parameter to the variance matrix so that it is invertible.

Want more information? Have questions? Get answers in the JMP User Community (community.jmp.com).