A-ComVar: A Flexible Extension of Common Variance Designs

  • Shrabanti Chowdhury
  • Joshua Lukemire
  • Abhyuday MandalEmail author
Original Article


We consider nonregular fractions of factorial experiments for a class of linear models. These models have a common general mean and main effects; however, they may have different 2-factor interactions. Here we assume for simplicity that 3-factor and higher-order interactions are negligible. In the absence of a priori knowledge about which interactions are important, it is reasonable to prefer a design that results in equal variance for the estimates of all interaction effects to aid in model discrimination. Such designs are called common variance designs and can be quite challenging to identify without performing an exhaustive search of possible designs. In this work, we introduce an extension of common variance designs called approximate common variance or A-ComVar designs. We develop a numerical approach to finding A-ComVar designs that is much more efficient than an exhaustive search. We present the types of A-ComVar designs that can be found for different number of factors, runs, and interactions. We further demonstrate the competitive performance of both common variance and A-ComVar designs using several comparisons to other popular designs in the literature.


Class of models Model identification Common variance Plackett–Burman Adaptive lasso Approximate common variance Genetic algorithm 



  1. 1.
    Bingham DR, Chipman HA (2007) Incorporating prior information in optimal design for model selection. Technometrics 49(2):155–163MathSciNetCrossRefGoogle Scholar
  2. 2.
    Breiman L (1995) Better subset regression using the nonnegative garrote. Technometrics 37(4):373–384MathSciNetCrossRefGoogle Scholar
  3. 3.
    Calvin JA (1986) A new class of variance balanced designs. J Stat Plan Inference 14(2–3):251–254MathSciNetCrossRefGoogle Scholar
  4. 4.
    Candes E, Tao T (2007) The Dantzig selector: statistical estimation when p is much larger than n. Ann Stat 35(6):2313–2351MathSciNetCrossRefGoogle Scholar
  5. 5.
    Cheng C-S (1986) A method for constructing balanced incomplete-block designs with nested rows and columns. Biometrika 73(3):695–700MathSciNetCrossRefGoogle Scholar
  6. 6.
    Chowdhury S (2016) Common variance fractional factorial designs for model comparisons. PhD thesis, University of California RiversideGoogle Scholar
  7. 7.
    Ghosh S, Chowdhury S (2017) CV, ECV, and robust CV designs for replications under a class of linear models in factorial experiments. J Stat Plan Inference 188:1–7MathSciNetCrossRefGoogle Scholar
  8. 8.
    Ghosh S, Flores A (2013) Common variance fractional factorial designs and their optimality to identify a class of models. J Stat Plan Inference 143(10):1807–1815MathSciNetCrossRefGoogle Scholar
  9. 9.
    Ghosh S, Tian Y (2006) Optimum two level fractional factorial plans for model identification and discrimination. J Multivar Anal 97(6):1437–1450MathSciNetCrossRefGoogle Scholar
  10. 10.
    Gupta S, Jones B (1983) Equireplicate balanced block designs with unequal block sizes. Biometrika 70(2):433–440MathSciNetCrossRefGoogle Scholar
  11. 11.
    Hedayat A, Stufken J (1989) A relation between pairwise balanced and variance balanced block designs. J Am Stat Assoc 84(407):753–755MathSciNetCrossRefGoogle Scholar
  12. 12.
    Kane A, Mandal A (2019) A new analysis strategy for designs with complex aliasing. Am Stat. CrossRefGoogle Scholar
  13. 13.
    Khatri C (1982) A note on variance balanced designs. J Stat Plan Inference 6(2):173–177MathSciNetCrossRefGoogle Scholar
  14. 14.
    Li W, Nachtsheim CJ (2000) Model-robust factorial designs. Technometrics 42(4):345–352CrossRefGoogle Scholar
  15. 15.
    Lin CD, Anderson-Cook CM, Hamada MS, Moore LM, Sitter RR (2015) Using genetic algorithms to design experiments: a review. Qual Reliab Eng Int 31(2):155–167CrossRefGoogle Scholar
  16. 16.
    Mandal A, Wong WK, Yu Y (2015) Algorithmic searches for optimal designs. In: Dean A, Morris M, Stufken J, Bingham D (eds) Handbook of design and analysis of experiments. Chapman & Hall/CRC, Boca Raton, FL, pp 755–783Google Scholar
  17. 17.
    Mukerjee R, Kageyama S (1985) On resolvable and affine resolvable variance-balanced designs. Biometrika 72(1):165–172MathSciNetCrossRefGoogle Scholar
  18. 18.
    Srivastava J (1976) Some further theory of search linear models. In: Contribution to applied statistics. Swiss-Australian Region of Biometry Society, pp 249–256Google Scholar
  19. 19.
    Srivastava J, Ghosh S (1976) A series of balanced factorial designs of resolution v which allow search and estimation of one extra unknown effect. Sankhyā Indian J Stat Ser B 38:280–289MathSciNetzbMATHGoogle Scholar
  20. 20.
    Srivastava J, Gupta B (1979) Main effect plan for 2m factorials which allow search and estimation of one unknown effect. J Stat Plan Inference 3(3):259–265CrossRefGoogle Scholar
  21. 21.
    Yuan M, Joseph VR, Lin Y (2007) An efficient variable selection approach for analyzing designed experiments. Technometrics 49(4):430–439MathSciNetCrossRefGoogle Scholar
  22. 22.
    Yuan M, Joseph VR, Zou H (2009) Structured variable selection and estimation. Ann Appl Stat 3(4):1738–1757MathSciNetCrossRefGoogle Scholar

Copyright information

© Grace Scientific Publishing 2020

Authors and Affiliations

  • Shrabanti Chowdhury
    • 1
  • Joshua Lukemire
    • 2
  • Abhyuday Mandal
    • 3
    Email author
  1. 1.Department of Genetics and Genomic SciencesIcahn School of Medicine at Mount SinaiNew YorkUSA
  2. 2.Department of Biostatistics and BioinformaticsEmory UniversityAtlantaUSA
  3. 3.Department of StatisticsUniversity of GeorgiaAthensUSA

Personalised recommendations