generateX0 {MCMChybridGP} | R Documentation |
A function to randomly generate n0
-many points
within requested bounds, lb
, ub
.
The points selected are to have the largest, minimum
distance between any two points.
generateX0 (lb, ub, n0 = 10, npool = 100, ranX = NULL)
lb |
Lower (finite) bounds for points generated. |
ub |
Upper (finite) bounds for points generated. |
n0 |
The number of points to be generated. |
npool |
The number of sets of randomly generated points to be considered in determining the best set. |
ranX |
An optional function to generate a random set of points to be considered. |
A matrix is returned which can then be supplied to hybrid.explore
.
Mark James Fielding <stafmj@nus.edu.sg>
"Efficient MCMC schemes for Bayesian calibration of computer models", Fielding, Mark, Nott, David J. and Liong Shie-Yui (2009), in preparation.
lb <- c(-3,-3) ub <- c(3,3) X0 <- generateX0(lb, ub) ## Or with 'ranX' supplied: ranX <- function() matrix(rnorm(40),ncol=2) X1 <- generateX0(lb, ub, n0=20, ranX=ranX)