multiDimLHS: Multidimensional Latin Hypercube Sampling (LHS) generation

In qle: Simulation-Based Quasi-Likelihood Estimation

Description

The function generates or augments a multidimensional design in a hyperbox.

Usage

multiDimLHS(N, lb, ub, method = c("randomLHS", "maximinLHS",
  "augmentLHS"), X = NULL, type = c("list", "matrix"))

Arguments

N	number of points to randomly select or augment an existing sample set
lb	lower bounds defining the (hyper)box of the parameter search space
ub	upper bounds defining the (hyper)box of the parameter search space
method	type of sampling, 'randomLHS', 'maximinLHS' or 'augmentLHS'
X	optional, matrix of existing sample points, NULL (default), for augmentation only
type	either "list" or "matrix" as return type

Value

Either return a list or matrix of sampled vectors or newly generated points if an existing sample set was to be augmented.

Author(s)

M. Baaske

See Also

randomLHS, maximinLHS, augmentLHS

Examples

data(normal)
# generate a design
X <- multiDimLHS(N=5,qsd$lower,qsd$upper,type="matrix")

# augment design X 
rbind(X,multiDimLHS(N=1,qsd$lower,qsd$upper,X=X,
				method="augmentLHS",type="matrix"))

qle documentation built on May 2, 2019, 9:55 a.m.