Learn R Programming

pse (version 0.3.4)

target.sbma: Adaptative generation of Latin Hypercubes

Description

Generates a series of Latin Hypercube Samples for a model until a pair of LHS present a measure of agreement equal to or greater than a specified target.

Usage

target.sbma(target, model, factors, q = NULL, q.arg = NULL, res.names = NULL, 
			method=c("HL", "random"), opts=list(), init, inc, FUN = min)

Arguments

target
The desired SBMA.
model
The function to be run, representing the model or simulation. If NULL, no function is run and the object generated is incomplete, see also the 'tell' method.
factors
The names of the input variables (used for naming the 'data' data.frame and in plotting)
q
The quantile functions to be used. If only one is provided, it will be used for all parameters.
q.arg
A list containing the arguments for the 'q' functions. Each parameter must be specified by a named list, containing all of the arguments for the quantile distribution.
res.names
Optional: what are the names of the model results? (Used mainly for plotting)
method
The desired method for the generation of the hypercubes. Please refer to the LHS help page.
opts
Additional options for the method chosen. Please refer to the LHS help page.
init
The size of the initial LHS generated.
inc
The increment between successive runs. For example, if init = 5 and inc = 20, the first LHS will be generated with size 5, the second with size 25.
FUN
When the model returns more than one response, SBMA values are calculated for each variable. The FUN argument specifies how to combine these SBMA values. The recommended default is to chose the minimum value.

Value

  • Returns the largest LHS generated.