DiceDesign (version 1.10)

NOLHdesigns: List of Cioppa's Nearly Orthogonal Latin Hypercubes designs

Description

A list of the NOLH designs for 2 to 29 input variables proposed by Cioppa in 2007. These designs combine a latin structure, orthogonality between the main terms and the interactions (+ squares) and reduced correlations between the interactions (+ squares).

This list combines the Excel spreadsheets published by Sanchez (see Source). It is used internally by the function nolhDesign which provides various normalizations.

Usage

NOLHdesigns

Format

A list of 5 matrices representing designs of experiments for 8 to 29 input variables:

nolh2_7:

2 to 7 input variables, 17 experiments.

nolh8_11:

8 to 11 input variables, 33 experiments.

nolh12_16:

12 to 16 input variables, 65 experiments.

nolh17_22:

17 to 22 input variables, 129 experiments.

nolh23_29:

23 to 29 input variables, 257 experiments.

Author

T.M. Cioppa for the designs. P. Kiener for the R code.

References

Cioppa T.M., Lucas T.W. (2007). Efficient nearly orthogonal and space-filling Latin hypercubes. Technometrics 49, 45-55.

Kleijnen, J.P.C., Sanchez S.M., T.W. Lucas and Cioppa T. M.. A user's guide to the brave new world of designing simulation experiments. INFORMS Journal on Computing 17(3): 263-289.

Ye, K. Q. (1998). Orthogonal Latin hypercubes and their application in computer experiments. J. Amer. Statist. Asso. 93, 1430- 1439.

See Also

The main function nolhDesign. De Rainville's NOLH design list: NOLHDRdesigns.

Examples

## data(NOLHdesigns)

## all matrices 
names(NOLHdesigns)
lapply(NOLHDRdesigns, tail, 2)

## The first matrix/design
NOLHdesigns[["nolh2_7"]]