An algorithm for finding efficient test-control block designs with correlated observations

Abstract

The theory of optimal test-control block designs provides guidance on treatments allocation in experimental units. However, it is theoretically difficult to find them; therefore, the availability of an efficient and user-friendly algorithm for finding the optimal designs is essential for both researchers and practitioners. This paper describes an algorithm for constructing efficient test-control incomplete block designs with correlated observations. In order to evaluate the algorithm, we compare our results with the optimal designs presented in some published papers. An advantage of our algorithm is its independency to the size of blocks and the structure of correlation. Also, it takes to run between 30 s and 10 min depending on the type of CPU processor and the design.

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

Fig. 1

References

  1. Angelis L (2003) An evolutionary algorithm for A-optimal incomplete block designs. J Stat Comput Simul 73(10):753–771

    MathSciNet  MATH  Article  Google Scholar 

  2. Chatterjee A, Siarry P (2006) Nonlinear inertia weight variation for dynamic adaptation in particle swarm optimization. Comput Oper Res 33(3):859–871

    MATH  Article  Google Scholar 

  3. Cutler DR (1993) Efficient block designs for comparing test treatments to a control when the errors are correlated. J Stat Plan Inference 36(1):107–125

    MathSciNet  MATH  Article  Google Scholar 

  4. Das A, Dey A, Kageyama S, Sinha K (2005) A-efficient balanced treatment incomplete block designs. Aust J Comb 32:243–252

    MathSciNet  MATH  Google Scholar 

  5. Eberhart RC, Shi Y (2000) Comparing inertia weights and constriction factors in particle swarm optimization. In: Proceedings of the 2000 congress on evolutionary computation. CEC00 (Cat. No. 00TH8512), vol 1. IEEE, pp 84–88

  6. Fan SKS, Chang JM (2007) A modified particle swarm optimizer using an adaptive dynamic weight scheme. In: International conference on digital human modeling. Springer, Berlin, pp 56–65

  7. Hero A, Rajaratnam B (2012) Hub discovery in partial correlation graphs. IEEE Trans Inf Theory 58(9):6064–6078

    MathSciNet  MATH  Article  Google Scholar 

  8. Iqbal I, Tahir MH (2008) Construction of test-control treatment block designs when \(k> v\). Aligarh J Stat 28:55–73

    MathSciNet  MATH  Google Scholar 

  9. Jones B (1976) An algorithm for deriving optimal block designs. Technometrics 18(4):451–458

    MathSciNet  MATH  Article  Google Scholar 

  10. Jones B, Eccleston JA (1980) Exchange and interchange procedures to search for optimal designs. J R Stat Soc Ser B (Methodolo) 42(2):238–243

    MathSciNet  MATH  Google Scholar 

  11. Kennedy J, Eberhart R (1995). Particle swarm optimization (PSO). In: Proceedings of IEEE international conference on neural networks IV, Perth, Australia, pp 1942–1948

  12. Kirkpatrick S, Gelatt CD, Vecchi MP (1983) Optimization by simulated annealing. Science 220(4598):671–680

    MathSciNet  MATH  Article  Google Scholar 

  13. Kunert J, Martin RJ, Eccleston J (2010) Optimal block designs comparing treatments with a control when the errors are correlated. J Stat Plan Inference 140(9):2719–2738

    MathSciNet  MATH  Article  Google Scholar 

  14. Li C, Coster DC (2014) A simulated annealing algorithm for D-optimal design for 2-way and 3-way polynomial regression with correlated observations. J Appl Math 2014:1–7

    Google Scholar 

  15. Li C, Coster DC (2015) Construction of weak universal optimal block designs with various correlation structures and block sizes. J Stat Plan Inference 160:1–10

    MathSciNet  MATH  Article  Google Scholar 

  16. Majumdar D, Notz WI (1983) Optimal incomplete block designs for comparing treatments with a control. Ann Stat 11(1):258–266

    MathSciNet  MATH  Article  Google Scholar 

  17. Martin RJ, Eccleston JA (1992) Recursive formulae for constructing block designs with dependent errors. Biometrika 79(2):426–430

    MathSciNet  MATH  Article  Google Scholar 

  18. Martin RJ, Eccleston JA (2001) Optimal and near-optimal designs for dependent observations. Stat Appl 3(1,2):101–116

    MathSciNet  Google Scholar 

  19. Mitchell T.J. (1973) Computer construction of small D-optimal incomplete block designs. In: Proceedings of the 39th session of the ISI, vol 2, pp 199–205

  20. Nguyen NK (1994) Construction of optimal block designs by computer. Technometrics 36(3):300–307

    MathSciNet  MATH  Article  Google Scholar 

  21. Nguyen NK, Dey A (1990) Computer-aided construction of small (M, S)-optimal incomplete block designs. Aust J Stat 32(3):399–410

    MathSciNet  MATH  Article  Google Scholar 

  22. Rathore A, Parsad R, Gupta VK (2006) Computer aided search of efficient block designs for making all possible pairwise treatment comparisons. J Stat Appl J Forum Interdis Math 1:15–33

    Google Scholar 

  23. Russell KG, Eccleston JA, Knudsen GJ (1981) Algorithms for the construction of (M, S)-optimal block designs and row-column designs. J Stat Comput Simul 12(2):93–105

    MathSciNet  MATH  Article  Google Scholar 

  24. Satpati SK, Parsad R, Gupta VK (2007) Efficient block designs for dependent observations—a computer-aided search. Commun Stat Theory Method 36(6):1187–1223

    MathSciNet  MATH  Article  Google Scholar 

  25. Shi Y, Eberhart R (1998a) A modified particle swarm optimizer. In: 1998 IEEE international conference on evolutionary computation proceedings. IEEE world congress on computational intelligence (Cat. No. 98TH8360). IEEE, pp 69–73

  26. Shi Y, Eberhart R.C (1998b) Parameter selection in particle swarm optimization. In: International conference on evolutionary programming. Springer, Berlin, pp 591–600

  27. Zergaw GA (1989) Sequential method of constructing optimal block designs. Aust J Stat 31(2):333–342

    MathSciNet  MATH  Article  Google Scholar 

  28. Zhu Z, Coster DC (2004) Weak universal optimal block designs for correlated observations. PhD dissertation, Department of mathematics and statistics, Utah State University

Download references

Acknowledgements

This paper is a part of the second author?s Ph.D. thesis. Author’s would like to thank the editor-in-chief and reviewers for their constructive and helpful comments which considerably led to improving the quality of the initial draft of the paper.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Mahboobeh Doosti-Irani.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Pooladsaz, S., Doosti-Irani, M. An algorithm for finding efficient test-control block designs with correlated observations. Comput Stat 35, 821–836 (2020). https://doi.org/10.1007/s00180-019-00904-z

Download citation

Keywords

  • PSO algorithm
  • SA algorithm
  • \(A_{tc}\)-optimal
  • Near-optimal designs
  • \(A_{tc}\)-efficiency