Journal of Statistical Theory and Practice

, Volume 7, Issue 4, pp 732–744 | Cite as

On the Connectivity Problem for m-Way Designs

  • J. D. GodolphinEmail author


The problem of ascertaining conditions that ensure that an m-way design is connected has occupied the attention of research workers for very many years. One of the significant advances, as well as one of the earliest contributions, was provided by the classic work of J. N. Srivastava and D. A. Anderson in 1970, which gives a necessary and sufficient rank condition for an m-way design to be completely connected. In this article it is shown that the class of estimable parametric functions for an individual factor is derived directly from a simple extension of the Srivastava-Anderson result. This takes the form of a necessary and sufficient rank condition that is expressed in terms of the dimension of a segregated component of the kernel of the design matrix. The result has the interesting property that the connectivity status for all of the individual factors can be found simultaneously. Furthermore, it enables the formulation of several general results, which include the specification of conditions on designs exhibiting adjusted orthogonality. A number of examples are given to illustrate these results.


Adjusted orthogonality Connectivity Estimability Information matrix Kernel space Segregated component space 

AMS Subject Classification

62K99 62K10 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bérubé, J., and G. P. H. Styan. 1993. Decomposable three-way layouts. J. Stat. Plan. Inference, 36, 311–322.MathSciNetCrossRefGoogle Scholar
  2. Birkes, D., Y. Dodge, and J. Seely. 1976. Spanning sets for estimable contrasts in classification models. Ann. Stat., 4, 86–107.MathSciNetCrossRefGoogle Scholar
  3. Bose, R.C. 1944. The fundamental theorem in linear estimation. Proc. 31st Ind. Sci. Congress, 2–3 (abstract).Google Scholar
  4. Butz, L. 1982. Connectivity in multi-factor designs. Berlin, Germany: Heldermann Verlag.zbMATHGoogle Scholar
  5. Ceranka, B., and M. Kozlowska. 1991. Connectedness of row and column designs. Zast. Mat. Appl. Math. 21, 27–31.MathSciNetzbMATHGoogle Scholar
  6. Chakrabarti, M. C. 1963. On the C-matrix in design of experiments. J. Indian Stat. Assoc., 1, 23.MathSciNetGoogle Scholar
  7. Christensen, R. 2002. Plane answers to complex questions, 3rd ed. New York, NY, Springer.CrossRefGoogle Scholar
  8. Dodge, Y. 1985. Analysis of experiments with missing data. New York, NY, Wiley.zbMATHGoogle Scholar
  9. Eccleston, J., and A. S. Hedayat. 1974. On the theory of connected designs: Characterisation and optimality. Ann. Stat., 2, 1238–1255.CrossRefGoogle Scholar
  10. Eccleston, J., and K. Russell. 1975. Connectedness and orthogonality in multi-factor designs. Biometrika, 62, 341–345.MathSciNetCrossRefGoogle Scholar
  11. Eccleston, J., and K. Russell. 1977. Adjusted orthogonality in non-orthogonal designs. Biometrika, 64, 339–345.MathSciNetCrossRefGoogle Scholar
  12. Ghosh, S. 1986. On a new graphical method of determining the connectedness in three dimensional designs. Sankya, B 48, 207–215.MathSciNetzbMATHGoogle Scholar
  13. Godolphin, J. D. 2004. Simple pilot procedures for the avoidance of disconnected experimental designs. Appl. Stat., 53, 133–147.MathSciNetzbMATHGoogle Scholar
  14. Godolphin, J. D., and E. J. Godolphin. 2001. On the connectivity of row-column designs. Util. Math., 60, 51–65.MathSciNetzbMATHGoogle Scholar
  15. Harville, D. A. 1997. Matrix algebra from a statistician’s perspective. New York, NY, Springer.CrossRefGoogle Scholar
  16. John, J.A., and E. R. Williams, 1995. Cyclic and computer generated designs, 2nd ed. London, UK, Chapman and Hall.CrossRefGoogle Scholar
  17. Katyal, V., and S. Pal. 1991. Analysis and connectedness of four-dimensional designs. J. Indian Soci. Agri. Stat., 43, 296–309.MathSciNetGoogle Scholar
  18. Park, D. K., and A. M. Dean. 1990. Average efficiency factors and adjusted orthogonality in multidimensional designs. J. R. Stat. Soc., Ser. B, 52, 361–368.MathSciNetzbMATHGoogle Scholar
  19. Park, D.K., and K. R. Shah. 1995. On the connectedness of row-column designs. Commun. Stat., 24, 87–96.MathSciNetCrossRefGoogle Scholar
  20. Preece, D.A. 1996. Multifactor balanced designs with complete adjusted orthogonality for all pairs of treatment factors. Aust. J. Stat., 38, 223–230.CrossRefGoogle Scholar
  21. Raghavarao, D., and W. T. Federer. 1975. On connectedness in two-way elimination of heterogeneity designs. Ann. Stat., 2, 730–735.MathSciNetCrossRefGoogle Scholar
  22. Searle, S. R. 1987. Linear models for unbalanced data. New York, NY, Wiley.zbMATHGoogle Scholar
  23. Sengupta, D., and S. R. Jammalamadaka. 2003. Linear models: an integrated approach. London, UK, World Scientific.CrossRefGoogle Scholar
  24. Shah, K. R., and Y. Dodge. 1977. On the connectedness of designs. Sankya, B 39, 284–287.MathSciNetzbMATHGoogle Scholar
  25. Shah, K. R., and C. G. Khatri. 1973. Connectedness in row-column designs. Commun. Stat., 2, 571–573.MathSciNetCrossRefGoogle Scholar
  26. Srivastava, J. N., and D. A. Anderson. 1970. Some basic properties of multidimensional partially balanced designs. Ann. Math. Stat., 41, 1438–1445.MathSciNetCrossRefGoogle Scholar
  27. Wynn, H. P. 2008. Algebraic solutions to the connectivity problem for m-way layouts: Interaction-contrast aliasing. J. Stat. Plan. Inference, 138, 259–271.MathSciNetCrossRefGoogle Scholar

Copyright information

© Grace Scientific Publishing 2013

Authors and Affiliations

  1. 1.Department of MathematicsUniversity of SurreyGuildfordUK

Personalised recommendations