Maximal data information (MDI) prior for GP parameters (\(\sigma, \xi\))

Source: R/priors.R

For information about this and other priors see set_prior.

gp_mdi(pars, a = 1, min_xi = -1, max_xi = Inf, trendsd = 0)

Arguments

pars

A numeric vector of length 2. GP parameters (\(\sigma, \xi\)).

a

A numeric scalar. The default value of 1 gives the MDI prior.

min_xi

A numeric scalar. Prior lower bound on \(\xi\). Must not be -Inf because this results in an improper posterior. See Northrop and Attalides (2016) for details.

max_xi

A numeric scalar. Prior upper bound on \(\xi\).

trendsd

Has no function other than to achieve compatibility with function in the evdbayes package.

Value

The log of the prior density.

References

Northrop, P.J. and Attalides, N. (2016) Posterior propriety in Bayesian extreme value analyses using reference priors Statistica Sinica, 26(2), 721--743 doi:10.5705/ss.2014.034 .