Latin Hypercube Sampling

Description

Draws a Latin Hypercube Sample from a set of uniform distributions for use in creating a Latin Hypercube Design. The following parameters are available for fine tuning of the algorithm:

Random LHS:
- “Number of experiments”
OptimumLHS:
- “Number of experiments”
- “Maximum applications of the CP algorithm”
- “Optimal stopping criterion”
Improved LHS:
- “Number of experiments”
- “Number of candidate points used in the search”
Maximin LHS
- “Number of experiments”
- “Number of candidate points used in the search”

The resulting analysis is a simple “pairs” plot:

Source

References

Stocki, R. (2005) A method to improve design reliability using optimal Latin hypercube sampling _Computer Assisted Mechanics and Engineering Sciences_ *12*, 87-105.
Beachkofski, B., Grandhi, R. (2002) Improved Distributed Hypercube Sampling _American Institute of Aeronautics and Astronautics Paper_ *1274*. This function is based on the MATLAB program written by John Burkardt and modified 16 Feb 2005 http://www.csit.fsu.edu/~burkardt/m_src/ihs/ihs.m
Stein, M. (1987) Large Sample Properties of Simulations Using Latin Hypercube Sampling. _Technometrics_. *29*, 143-151.

Implementation

This LHS algorithms are wrapped from the [R] package LHS .

Installation

copy
RandomLHS.jar
in “Promethee_Install_Path/plugins/doe directory”,
restart Promethee GUI.