fit.gpr.sim.model


    A model object obtained as the return value from <code>eval.on.grid</code>.


model


    Start value passed on to <code>optim</code> when performing the marginal
  likelihood optimisation to find appropriate values for the
  hyperparameters for the GPR regression function.


start


    Set to <code>TRUE</code> if gradient information should be passed to
    <code>optim</code>. If false, <code>optim</code> uses a finite difference
    approximation of the gradient when performing the optimisation of the hyperparameters.



    The optimisation method to be used by <code>optim</code>. One of
  <code>"Nelder-Mead"</code>, <code>"BFGS",</code> <code>"CG"</code>, <code>"L-BFGS-B"</code>,
  <code>"SANN"</code> or <code>"Brent"</code>.


method


    A numeric, atomic vector containing the lower limits for the
  hyperparameters. The first entry is for the standard deviation
  parameter and the remaining entries are for the length parameters.
  If supplied, all elements must be >= 0.


lower


    A numeric, atomic vector containing the upper limits for the
  hyperparameters. The first entry is for the standard deviation
  parameter and the remaining entries are for the length parameters.


upper


    A list of control parameters passed on to <code>optim</code>.


control


  <code>fit.gpr</code> method for objects of class <code>sim.model</code>.


Optimisation of the expected utility in single-stage and multi-stage Bayesian decision problems. The expected utility is estimated by simulation. For single-stage problems, JAGS is used to draw MCMC samples.

fit.gpr.sim.model: Fit A Gaussian Process Regression Function

Description

Usage

Arguments

Details