Description Usage Arguments Value Author(s)
This constructs a focused proposal to make a metropolis-hasting update of the lambda parameter in a Gaussian process. It is agnostic to which model component in the spatial GEV the GP belongs to.
1 | gev.update.lambda(tau, alpha, lambda, D, a, b)
|
tau |
A vector of the random effects |
alpha |
The global precision of the Gaussian process |
lambda |
The current value of lambda |
D |
The matrix of distances between the points associated with the vector tau |
a |
The parameter for the prior of lambda |
b |
The second parameter for the prior of lambda |
A scalar which is the updated value of lambda.
Alex Lenkoski <alex@nr.no>
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.