Skip to main content
Download PDF

D-optimal designs via a cocktail algorithm

Statistics and Computing volume 21, pages 475–481 (2011)Cite this article

Abstract

A fast new algorithm is proposed for numerical computation of (approximate) D-optimal designs. This cocktail algorithm extends the well-known vertex direction method (VDM; Fedorov in Theory of Optimal Experiments, 1972) and the multiplicative algorithm (Silvey et al. in Commun. Stat. Theory Methods 14:1379–1389, 1978), and shares their simplicity and monotonic convergence properties. Numerical examples show that the cocktail algorithm can lead to dramatically improved speed, sometimes by orders of magnitude, relative to either the multiplicative algorithm or the vertex exchange method (a variant of VDM). Key to the improved speed is a new nearest neighbor exchange strategy, which acts locally and complements the global effect of the multiplicative algorithm. Possible extensions to related problems such as nonparametric maximum likelihood estimation are mentioned.

References

  • Atkinson, A.C., Chaloner, K., Herzberg, A.M., Juritz, J.: Optimum experimental designs for properties of a compartmental model. Biometrics 49, 325–337 (1993)

    MATH  Article  Google Scholar 

  • Atkinson, A.C., Donev, A.N., Tobias, R.D.: Optimum Experimental Designs, with SAS. Oxford University Press, London (2007)

    MATH  Google Scholar 

  • Atwood, C.L.: Convergent design sequences for sufficiently regular optimality criteria. Ann. Stat. 4, 1124–1138 (1976)

    MATH  Article  MathSciNet  Google Scholar 

  • Böhning, D.: A vertex-exchange-method in D-optimal design theory. Metrika 33, 337–347 (1986)

    MATH  Article  MathSciNet  Google Scholar 

  • Dette, H., Melas, V.B., Wong, W.K.: Locally D-optimal designs for exponential regression models. Stat. Sin. 16, 789–803 (2006)

    MATH  MathSciNet  Google Scholar 

  • Dette, H., Pepelyshev, A., Zhigljavsky, A.: Improving updating rules in multiplicative algorithms for computing D-optimal designs. Comput. Stat. Data Anal. 53, 312–320 (2008)

    MATH  Article  MathSciNet  Google Scholar 

  • Fedorov, V.V.: Theory of Optimal Experiments. Academic Press, New York (1972). (Transl. and ed. by W.J. Studden, E.M. Klimko)

    Google Scholar 

  • Haines, L.M.: A class of equivalent problems in statistics and operational research. S. Afr. Stat. J. 32, 43–66 (1998)

    MATH  Google Scholar 

  • Harman, R., Pronzato, L.: Improvements on removing nonoptimal support points in D-optimum design algorithms. Stat. Probab. Lett. 77, 90–94 (2007)

    MATH  Article  MathSciNet  Google Scholar 

  • Jongbloed, G.: The iterative convex minorant algorithm for nonparametric estimation. J. Comput. Graph. Stat. 7, 310–321 (1998)

    Article  MathSciNet  Google Scholar 

  • Kiefer, J.: General equivalence theory for optimum designs (approximate theory). Ann. Stat. 2, 849–879 (1974)

    MATH  Article  MathSciNet  Google Scholar 

  • Kiefer, J., Wolfowitz, J.: The equivalence of two extremum problems. Can. J. Math. 12, 363–366 (1960)

    MATH  Article  MathSciNet  Google Scholar 

  • Lindsay, B.G.: The geometry of mixture likelihoods: a general theory. Ann. Stat. 11, 86–94 (1983)

    MATH  Article  MathSciNet  Google Scholar 

  • Mandal, S., Torsney, B.: Construction of optimal designs using a clustering approach. J. Stat. Plan. Inference 136, 1120–1134 (2006)

    MATH  Article  MathSciNet  Google Scholar 

  • Pázman, A.: Foundations of Optimum Experimental Design. Reidel, Dordrecht (1986)

    MATH  Google Scholar 

  • Pukelsheim, F.: Optimal Design of Experiments. Wiley, New York (1993)

    MATH  Google Scholar 

  • Silvey, S.D., Titterington, D.M., Torsney, B.: An algorithm for optimal designs on a finite design space. Commun. Stat. Theory Methods 14, 1379–1389 (1978)

    Google Scholar 

  • Titterington, D.M.: Algorithms for computing D-optimal design on finite design spaces. In: Proc. of the 1976 Conf. on Information Science and Systems, vol. 3, pp. 213–216. John Hopkins Press, Baltimore (1976)

    Google Scholar 

  • Titterington, D.M.: Estimation of correlation coefficients by ellipsoidal trimming. Appl. Stat. 27, 227–234 (1978)

    MATH  Article  Google Scholar 

  • Wang, Y.: Dimension-reduced nonparametric maximum likelihood computation for interval-censored data. Comput. Stat. Data Anal. 52, 2388–2402 (2008)

    MATH  Article  Google Scholar 

  • Wellner, J.A., Zhan, Y.: A hybrid algorithm for computation of the nonparametric maximum likelihood estimator from censored data. J. Am. Stat. Assoc. 92, 945–959 (1997)

    MATH  Article  MathSciNet  Google Scholar 

  • Wu, C.F.: Some algorithmic aspects of the theory of optimal designs. Ann. Stat. 6, 1286–1301 (1978)

    MATH  Article  Google Scholar 

  • Wynn, H.P.: Results in the theory and construction of D-optimum experimental designs. J. R. Stat. Soc. Ser. B 34, 133–147 (1972)

    MATH  MathSciNet  Google Scholar 

  • Yu, Y.: Monotonic convergence of a general algorithm for computing optimal designs. Ann. Stat. 38, 1593–1606 (2010a). arXiv:0905.2646v3

    MATH  Article  Google Scholar 

  • Yu, Y.: Strict monotonicity and convergence rate of Titterington’s algorithm for computing D-optimal designs. Comput. Stat. Data Anal. 54, 1419–1425 (2010b)

    Article  Google Scholar 

  • Yu, Y.: Improved EM for mixture proportions with applications to nonparametric ML estimation for censored data. Preprint, arXiv:1002.3640 (2010c)

Download references

Author information

Authors and Affiliations

  1. Department of Statistics, University of California, Irvine, CA, 92697, USA

    Yaming Yu

Authors
  1. Yaming Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yaming Yu.

Rights and permissions

Open Access This is an open access article distributed under the terms of the Creative Commons Attribution Noncommercial License (https://creativecommons.org/licenses/by-nc/2.0), which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.

Reprints and Permissions

About this article

Cite this article

Yu, Y. D-optimal designs via a cocktail algorithm. Stat Comput 21, 475–481 (2011). https://doi.org/10.1007/s11222-010-9183-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11222-010-9183-2

Keywords

  • D-optimality
  • Experimental design
  • Hybrid algorithm