Latinized Partially Stratified Sampling

Generate random samples of an nD random vector using Latinized Partially Stratified Sampling
187 Downloads
Updated 11 Jan 2016

View License

The LPSS code generates n-dimensional uniform samples on [0,1] according to the latinized partially stratified sampling methodology. The method serves to generalize the Latin hypercube sampling method such that stratification occurs on subdomains of user-prescribed dimension. The method is described in detail in:
Shields, M.D. and Zhang, J. (2016). "The generalization of Latin hypercube sampling." Reliability Engineering and System Safety. 148: 96-108.
A simple demonstration is provided that shows graphically how a five dimensional sample can be constructed according to stratification on two 2-dimensional subdomains and one 1-dimensional subdomain.

Code for application to a 6-dimensional plate buckling problem presented by Shields and Zhang is also provided.

Cite As

Michael Shields (2026). Latinized Partially Stratified Sampling (https://uk.mathworks.com/matlabcentral/fileexchange/54847-latinized-partially-stratified-sampling), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2015b
Compatible with any release
Platform Compatibility
Windows macOS Linux
Version Published Release Notes
1.0.0.0