# The use of latin hypercube sampling for the efficient estimation of confidence intervals

## Abstract

Latin hypercube sampling (LHS) has long been used as a way of assuring adequate sampling of the tails of distributions in a Monte Carlo analysis and provided the framework for the uncertainty analysis performed in the NUREG-1150 risk assessment. However, this technique has not often been used in the performance of regulatory analyses due to the inability to establish confidence levels on the quantiles of the output distribution. Recent work has demonstrated a method that makes this possible. This method is compared to the procedure of crude Monte Carlo using order statistics, which is currently used to establish confidence levels. The results of several statistical examples demonstrate that the LHS confidence interval method can provide a more accurate and precise solution, but issues remain when applying the technique generally. (authors)

- Authors:

- Ohio State Univ., 201 W 19th Ave, Columbus, OH 43210 (United States)
- New Jersey Inst. of Technology, 218 Central Ave, Newark, NJ 07102 (United States)

- Publication Date:

- Research Org.:
- American Nuclear Society, 555 North Kensington Avenue, La Grange Park, IL 60526 (United States)

- OSTI Identifier:
- 22107753

- Resource Type:
- Conference

- Resource Relation:
- Conference: ICAPP '12: 2012 International Congress on Advances in Nuclear Power Plants, Chicago, IL (United States), 24-28 Jun 2012; Other Information: Country of input: France; 26 refs.; Related Information: In: Proceedings of the 2012 International Congress on Advances in Nuclear Power Plants - ICAPP '12| 2799 p.

- Country of Publication:
- United States

- Language:
- English

- Subject:
- 22 GENERAL STUDIES OF NUCLEAR REACTORS; DATA COVARIANCES; DATA PROCESSING; FINANCIAL DATA; MONTE CARLO METHOD; NUCLEAR POWER PLANTS; RISK ASSESSMENT; SAMPLING; STATISTICS

### Citation Formats

```
Grabaskas, D., Denning, R., Aldemir, T., and Nakayama, M. K.
```*The use of latin hypercube sampling for the efficient estimation of confidence intervals*. United States: N. p., 2012.
Web.

```
Grabaskas, D., Denning, R., Aldemir, T., & Nakayama, M. K.
```*The use of latin hypercube sampling for the efficient estimation of confidence intervals*. United States.

```
Grabaskas, D., Denning, R., Aldemir, T., and Nakayama, M. K. Sun .
"The use of latin hypercube sampling for the efficient estimation of confidence intervals". United States.
```

```
@article{osti_22107753,
```

title = {The use of latin hypercube sampling for the efficient estimation of confidence intervals},

author = {Grabaskas, D. and Denning, R. and Aldemir, T. and Nakayama, M. K.},

abstractNote = {Latin hypercube sampling (LHS) has long been used as a way of assuring adequate sampling of the tails of distributions in a Monte Carlo analysis and provided the framework for the uncertainty analysis performed in the NUREG-1150 risk assessment. However, this technique has not often been used in the performance of regulatory analyses due to the inability to establish confidence levels on the quantiles of the output distribution. Recent work has demonstrated a method that makes this possible. This method is compared to the procedure of crude Monte Carlo using order statistics, which is currently used to establish confidence levels. The results of several statistical examples demonstrate that the LHS confidence interval method can provide a more accurate and precise solution, but issues remain when applying the technique generally. (authors)},

doi = {},

journal = {},

number = ,

volume = ,

place = {United States},

year = {2012},

month = {7}

}