Skip to main content
Log in

On the construction of nested orthogonal Latin hypercube designs

  • Published:
Metrika Aims and scope Submit manuscript

Abstract

Latin hypercube designs are widely used in designing computer experiments. In recent years, nested orthogonal Latin hypercube designs have been proposed in the literature. In this article, two general methods of constructing nested orthogonal Latin hypercube designs have been developed. The methods give many new nested orthogonal Latin hypercube designs with fewer number of runs as compared to existing nested orthogonal Latin hypercube designs.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Cioppa TM, Lucas TW (2007) Efficient nearly orthogonal and space-filling Latin hypercubes. Technometrics 49(1):45–55

    Article  MathSciNet  Google Scholar 

  • Dey A, Sarkar D (2016) A note on the construction of orthogonal Latin hypercube designs. J Combin Des 24:105–111

    Article  MathSciNet  Google Scholar 

  • Georgiou SD, Efthimiou I (2014) Some classes of orthogonal latin hypercube designs. Stat Sin 24:101–120

    MathSciNet  MATH  Google Scholar 

  • Lin CD, Bingham D, Sitter RR, Tang B (2010) A new and flexible method for constructing designs for computer experiments. Ann Stat 38(3):1460–1477

    Article  MathSciNet  Google Scholar 

  • Mandal BN, Dash S, Parui S, Parsad R (2016) Orthogonal latin hypercube designs with special reference to four factors. Stat Probab Lett 119:181–185

    Article  MathSciNet  Google Scholar 

  • McKay MD, Beckman RJ, Conover WJ (1979) Comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics 21(2):239–245

    MathSciNet  MATH  Google Scholar 

  • Parui S, Mandal BN, Parsad R, Dash S (2018) Orthogonal Latin hypercube designs for three columns. Utilitas Math 108:149–158

    MathSciNet  MATH  Google Scholar 

  • Qian PZG (2009) Nested latin hypercube designs. Biometrika 96(4):957–970

    Article  MathSciNet  Google Scholar 

  • Qian Z, Seepersad CC, Joseph VR, Allen JK, Wu CJ (2006) Building surrogate models based on detailed and approximate simulations. J Mech Des 128(4):668–677

    Article  Google Scholar 

  • Sun F, Liu M-Q, Lin DKJ (2009) Construction of orthogonal Latin hypercube designs. Biometrika 96:971–974

    Article  MathSciNet  Google Scholar 

  • Sun F, Liu M-Q, Lin DKJ (2010) Construction of orthogonal Latin hypercube designs with flexible run sizes. J Stat Plan Inference 140(11):3236–3242

    Article  MathSciNet  Google Scholar 

  • Sun F, Tang B (2017) A general rotation method for orthogonal latin hypercubes. Biometrika 104(2):465–472

    MathSciNet  MATH  Google Scholar 

  • Yang J, Liu M-Q, Lin DKJ (2014) Construction of nested orthogonal latin hypercube designs. Stat Sin 24:211–219

    MathSciNet  MATH  Google Scholar 

  • Yang X, Yang J, Lin DKJ, Liu M (2016) A new class of nested (nearly) orthogonal latin hypercube designs. Stat Sin 26(3):1249–1267

    MathSciNet  MATH  Google Scholar 

  • Ye KQ (1998) Orthogonal column Latin hypercubes and their application in computer experiments. J Am Stat Assoc 93(444):1430–1439

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Sukanta Dash.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix: Proof of Theorem 2

Appendix: Proof of Theorem 2

First we prove one dimensional uniformity of the constructed design for each layer. One dimensional uniformity of pth layer is obvious. Consider \((p-1)\)th layer \(L_{p-1}=(2^{p-1}L_1^{*T},2^{p-1}L_2^{*T})\). Since \(n = 0 \text { mod } 4\), let \(n=2^2t\) where t is a positive integer. Then, each column of \(L_{p-1}\) contains elements belonging to set \(\{-(2^{p}t-2^{p-2}), -(2^{p}t-3 \times 2^{p-2}),\ldots ,(2^{p}t-2^{p-2}), (2^{p}t-3 \times 2^{p-2}), -2^{p}t, -(2^{p}t-2 \times 2^{p-2}),\ldots ,2^{p}t, (2^{p}t-2 \times 2^{p-2})\}=\{-2^{p}t, -(2^{p}t-2^{p-2}), -(2^{p}t-2 \times 2^{p-2}),\ldots ,(2^{p}t-2 \times 2^{p-2}), (2^{p}t-2^{p-2}),2^{p}t\}\). Clearly, the elements are equally spaced with spacing \(2^{p-2}\). Consider \((p-2)\)th layer \(L_{p-2}\). It may be verified easily that elements of each column of \(L_{p-2}\) are in the set \(\{-2^{p}t, -(2^{p}t-2^{p-3}), -(2^{p}t-2 \times 2^{p-3}),\ldots ,(2^{p}t-2 \times 2^{p-3}), (2^{p}t-2^{p-3}),2^{p}t\}\), the spacing between the elements being \(2^{p-3}\). On similar lines, elements of each column of ith layer \(L_i, i=1,2,\ldots ,p-1\) are in the set \(\{-2^{p}t, -(2^{p}t-2^{i-1}), -(2^{p}t-2 \times 2^{i-1}),\ldots ,(2^{p}t-2 \times 2^{i-1}), (2^{p}t-2^{i-1}),2^{p}t\}\) with spacing \(2^{i-1}\) between the elements. Proof of orthogonality is straightforward extension of the proof of orthogonality given in Theorem 1. Also, \(L_p \subset L_{p-1} \subset \ldots \subset L_2\subset L_1\). This completes the proof.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dash, S., Mandal, B.N. & Parsad, R. On the construction of nested orthogonal Latin hypercube designs. Metrika 83, 347–353 (2020). https://doi.org/10.1007/s00184-019-00721-w

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00184-019-00721-w

Keywords

Navigation