Description Usage Arguments Details Value Author(s) References See Also Examples
View source: R/discrepancyCriteria.R
Compute discrepancy criteria.
1  discrepancyCriteria(design,type='all')

design 
a matrix (or a data.frame) corresponding to the design of experiments. The discrepancy criteria are computed for a design in the unit cube [0,1]^d. If this condition is not satisfied the design is automatically rescaled.  
type 
type of discrepancies (single value or vector) to be computed:

The discrepancy measures how far a given distribution of points deviates from a perfectly uniform one. Different L2 discrepancies are available in DiceDesign. For example, if we denote by Vol(J) the volume of a subset J of [0; 1]^d and A(X; J) the number of points of X falling in J, the L2 discrepancy is:
DL2 (X)^2 = \int_{[0,1]^d} [(A(X,J_{a,b})/n  Vol(J_{a,b})]^2 da db
where a = (a1; ... ; ad)', b = (b1;...; bd)' and J_{a,b} = [a1; b1) X ... X [ad;bd). The other L2discrepancies are defined according to the same principle with different form from the subset J. Among all the possibilities, discrepancyCriteria implements only the L2 discrepancies because it can be expressed analytically even for high dimension.
Centered L2discrepancy is computed using the analytical expression done by Hickernell (1998). The user will refer to Pleming and Manteufel (2005) to have more details about the wrap around discrepancy.
A list containing the L2discrepancies of the design
.
J. Franco, D. Dupuy & B. Iooss
Fang K.T, Li R. and Sudjianto A. (2006) Design and Modeling for Computer Experiments, Chapman & Hall.
Fang KT., Liu MQ., Qin H. and Zhou YD. (2018) Theory and application of uniform experimental designs. Springer.
Franco J. (2008) Planification d'experiences numerique en phase exploratoire pour la simulation des phenomenes complexes, PhD thesis, Ecole Nationale Superieure des Mines de Saint Etienne.
Hickernell F.J. (1998) A generalized discrepancy and quadrature error bound. Mathematics of Computation, 67, 299322.
Pleming J.B. and Manteufel R.D. (2005) Replicated Latin Hypercube Sampling, 46th Structures, Structural Dynamics & Materials Conference, 1621 April 2005, Austin (Texas) – AIAA 20051819.
distance criteria (coverage
, meshRatio
,
mindist
and phiP
)
1 2 3 4  dimension < 2
n < 40
X < matrix(runif(n*dimension), n, dimension)
discrepancyCriteria(X)

$DisC2
[1] 0.09338951
$DisL2
[1] 0.02563204
$DisL2star
[1] 0.05270735
$DisM2
[1] 0.1023848
$DisS2
[1] 0.2243227
$DisW2
[1] 1.889521
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.