Abstract
Simulation methods play a key role in the modelling of theoretical or actual physical systems. Such models can approximate the behaviour of the real system and provide insights into its operation. Well-determined input parameters are of prime importance for obtaining reliable simulations due to their impact on the performance of the simulation design. Among various strategies for producing input parameter samples is Latin hypercube design (LHD). LHDs are generated by Latin hypercube sampling (LHS), a type of stratified sampling that can be applied to multiple variables. LHS has proven to be an efficient and popular method; however, it misses some important elements. While LHS focuses on the parameter space aspects, this paper highlights five more aspects which may greatly impact the efficiency of sampling. In this paper, we do not provide solutions but rather bring up unanswered questions which could be missed during strategy planning on model simulation.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Note that randomness in probabilistic models cannot be included into the input to make the model deterministic, since the results represented as distributions rather than fixed values may reflect smoothness of the model which would be broken by fixing the seed to the random generator.
References
Becker, D.A.: Overview of advantages and drawbacks of different methods for sensitivity analysis in the context of performance assessment. In: 5th IGD-TP Technical Exchange Forum, Kalmar, Sweden (2014)
Ferreira, S.C., Bruns, R., et al.: Box-Behnken design: an alternative for the optimization of analytical methods. Anal. Chim. Acta 597(2), 179–186 (2007)
Giunta, A., Wojtkiewicz, S., et al.: Overview of modern design of experiments methods for computational simulations. In: Proceedings of the 41st AIAA Aerospace Sciences Meeting and Exhibit, AIAA-2003-0649 (2003)
Kleijnen, J., Sanchez, S., et al.: A user’s guide to the brave new world of designing simulation experiments. Center for Economic Research Discussion Paper (1) (2003)
McKay, M., Beckman, R., Conover, W.: A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics 42(1), 55–61 (2000)
Melnick, E., Everitt, B.: Encyclopedia of Quantitative Risk Analysis and Assessment, vol. 1. Wiley (2008)
Paxton, P., Curran, P., et al.: Monte carlo experiments: design and implementation. Struct. Equ. Model. 8(2), 287–312 (2001)
Roy, R.K.: Design of experiments using the Taguchi approach: 16 steps to product and process improvement. Wiley (2001)
Saltelli, A., Chan, K., et al.: Sensitivity Analysis, vol. 1. Wiley, NY (2000)
Vanaja, K., Shobha Rani, R.: Design of experiments: concept and applications of Plackett Burman design. Clin. Res. Regul. Aff. 24(1), 1–23 (2007)
Viana, F.A.: Things you wanted to know about the Latin hypercube design and were afraid to ask. In: 10th World Congress on Structural and Multidisciplinary Optimization, Orlando, Florida, USA (cf. p. 69) (2013)
Williams, P., Bowden, F.: Dynamic morphological exploration. In: Proceedings of the 22nd National Conference of the Australian Society for Operations Research (2013)
Winer, B.J., Brown, D.R., Michels, K.M.: Statistical Principles in Experimental Design, vol. 2. McGraw-Hill (1971)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Mazonka, O., Konstantinou, C. (2018). What Latin Hypercube Is Not. In: Sarker, R., Abbass, H., Dunstall, S., Kilby, P., Davis, R., Young, L. (eds) Data and Decision Sciences in Action. Lecture Notes in Management and Industrial Engineering. Springer, Cham. https://doi.org/10.1007/978-3-319-55914-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-55914-8_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-55913-1
Online ISBN: 978-3-319-55914-8
eBook Packages: EngineeringEngineering (R0)