Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Illustration of sampling-based methods for uncertainty and sensitivity analysis.

J C Helton1, F J Davis

  • 1Department of Mathematics, Arizona State University, Tempe 85287-1804, USA. jchelto@sandia.gov

Risk Analysis : an Official Publication of the Society for Risk Analysis
|June 29, 2002
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Severity of cognitive disability and mental health court determinations about fitness to stand trial.

Journal of intellectual disability research : JIDR·2018
Same author

An improved Geiger-counter arrangement for determination of radium content.

Journal of research of the National Bureau of Standards·2010
Same author

An in vitro assessment of the erosive potential of some designer drinks.

The European journal of prosthodontics and restorative dentistry·2001
Same author

Physical interaction between the MADS box of serum response factor and the TEA/ATTS DNA-binding domain of transcription enhancer factor-1.

The Journal of biological chemistry·2001
Same author

Performance assessment in support of the 1996 compliance certification application for the Waste Isolation Pilot Plant.

Risk analysis : an official publication of the Society for Risk Analysis·2000
Same author

A Monte Carlo procedure for the construction of complementary cumulative distribution functions for comparison with the EPA release limits for radioactive waste disposal.

Risk analysis : an official publication of the Society for Risk Analysis·1996

Latin hypercube sampling offers more stable uncertainty analysis results than random sampling. The best sensitivity analysis method depends on the specific test problem

Area of Science:

  • Computational science
  • Statistical modeling
  • Uncertainty quantification

Background:

  • Sampling-based methods are crucial for uncertainty and sensitivity analysis in complex models.
  • Choosing appropriate sampling and analysis techniques is vital for reliable results.

Purpose of the Study:

  • To evaluate and compare various sampling strategies for uncertainty analysis.
  • To assess the effectiveness of diverse sensitivity analysis measures across different problem types.

Main Methods:

  • Utilized a sequence of linear, monotonic, and nonmonotonic test problems.
  • Compared replicated random sampling with Latin hypercube sampling for uncertainty analysis.
  • Evaluated multiple sensitivity analysis measures including correlation coefficients, rank correlation coefficients, and regression-based methods.

Related Experiment Videos

Main Results:

  • Latin hypercube samples yielded more stable uncertainty analysis results compared to random samples.
  • The performance of sensitivity analysis measures varied based on problem characteristics: linear measures for linear problems, rank-based measures for monotonic problems, and pattern-search measures for nonmonotonic problems.

Conclusions:

  • Latin hypercube sampling is a more robust approach for uncertainty quantification.
  • The selection of sensitivity analysis techniques should be tailored to the specific properties of the test problems for optimal performance.