Large Sample Properties of Simulations Using Latin Hypercube Sampling

1987/05/01 by Michael Stein, Michael L. Stein · 15 citations
Engineering · Decision Sciences · #Dynamics and Control of Mechanical Systems #Probabilistic and Robust Engineering Design #Simulation Techniques and Applications

paper · doi:10.1080/00401706.1987.10488205

Abstract

Latin hypercube sampling (McKay, Conover, and Beckman 1979) is a method of sampling that can be used to produce input values for estimation of expectations of functions of output variables. The asymptotic variance of such an estimate is obtained. The estimate is also shown to be asymptotically normal. Asymptotically, the variance is less than that obtained using simple random sampling, with the degree of variance reduction depending on the degree of additivity in the function being integrated. A method for producing Latin hypercube samples when the components of the input variables are statistically dependent is also described. These techniques are applied to a simulation of the performance of a printer actuator.

Cited by

• Designs for Computer Experiments
• Grouped Latin Hypercube Designs with Controlled Correlations
• Correcting environmental sampling bias improves transferability of species distribution models
• Structural identification of super high arch dams using Gaussian process regression with improved salp swarm algorithm
• Multimodal Information Gain in Bayesian Design of Experiments
• Multi-Distributed Sampling Method to Optimize Physical-Informed Neural Networks for Solving Optical Solitons
• Physics-informed neural networks method in high-dimensional integrable systems
• Can Extensive Grassland Management Pay Off for Farmers Facing Drought Risks? A Cumulative Prospect Theory‐Based Approach
• Darboux transformation-based LPNN generating novel localized wave solutions
• A review of techniques for parameter sensitivity analysis of environmental models
• Global, regional, and national estimates of the impact of a maternal Klebsiella pneumoniae vaccine: A Bayesian modeling analysis
• Complex dynamics on the one-dimensional quantum droplets via time piecewise PINNs
• Causality-guided adaptive sampling method for physics-informed neural networks solving forward problems of partial differential equations
• Robust phylodynamic inference and model specification for HIV transmission dynamics
• Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s Next

Related

• LHS in LHS: A new expansion strategy for Latin hypercube sampling in simulation design
• Populations of models, Experimental Designs and coverage of parameter\n space by Latin Hypercube and Orthogonal Sampling
• Exploring multi-dimensional spaces: a Comparison of Latin Hypercube and Quasi Monte Carlo Sampling Techniques
• Estimates of the coverage of parameter space by Latin Hypercube and Orthogonal sampling: connections between Populations of Models and Experimental Designs
• Efficient Nearly Orthogonal and Space-Filling Latin Hypercubes