Estimation and Optimal Designing under Latent Variable Models for Paired Comparisons Studies via a Multiplicative Algorithm

Conference paper
Part of the Contributions to Statistics book series (CONTRIB.STAT.)


We consider:

1. The problem of estimating the parameters of latent variable models such as the Bradley Terry or Thurstone Model by the method of maximum likelihood, given data from a paired comparisons experiment. The parameters of these models can be taken to be weights which are positive and sum to one;

2. The problem of determining approximate locally optimal designs for good estimation of these parameters; i.e of determining optimal design weights which are also positive and sum to one.


Optimal Design Paired Comparison Latent Variable Model Thurstone Model Multiplicative Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bradley, R. A. and Terry, M. E. (1952). The rank analysis of incomplete block designs I, The method of paired comparisons. Biometrika 39, 324-345.MATHMathSciNetGoogle Scholar
  2. Bradley, R. A. and El-Helbawy, A. T. (1976). Treatment contrasts in paired comparisons: basic procedures with applications to factorials. Biometrika 63, 255-262.MATHCrossRefMathSciNetGoogle Scholar
  3. Kiefer, J. (1974) General equivalence theory for optimum designs (approximate theory) Annals of Statistics 2, 849-879.MATHCrossRefMathSciNetGoogle Scholar
  4. Kuk, A.C. Y. (1995). Modelling paired comparison data with large numbers of draws and large variability of draw percentages among players. Statistician 44, 523-528.CrossRefGoogle Scholar
  5. Mandal, S. and Torsney, B. (2000) Algorithms for the construction of optimising distributions. Communications in Statistics (Theory and Methods) 29, 1219-1231.MATHCrossRefMathSciNetGoogle Scholar
  6. Thurstone, L. L. (1927b). The method of paired comparisons for social values. Journal of Abnormal and Social Psychology 21, 384-400.CrossRefGoogle Scholar
  7. Torsney, B. (1988) Computing Optimizing Distributions with Applications in Design, Estimation and Image Processing. In Optimal Design and Analysis of Experiments (Y. Dodge, V.V. Fedorov and H.P. Wynn eds). Amsterdam: North Holland, 361-370.Google Scholar
  8. Torsney, B. (2004) Fitting Bradley Terry models using a multiplicative algorithm. In Proceedings in Computational Statistics (COMPSTAT2004) (J. Antoch, ed.).Heidelberg: Physica-Verlag, 214-226.Google Scholar
  9. Torsney, B. and Alahmadi, A. M. (1992) Further developments of algorithms for constructing optimizing distributions. In Model Oriented Data Analysis (Proceedings of 2nd IIASA- Workshop, St. Kyrik, Bulgaria, 1990) (V. Fedorov, W.G. Muller, I.N. Vuchkov eds). Heidelberg: Physica-Verlag, 121-129.Google Scholar
  10. Whittle, P. (1973). Some general points in the theory of optimal experimental design Journal of the Royal Statistical Society B 35, 123-130.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  1. 1.Department of StatisticsUniversity of GlasgowGlasgowUK

Personalised recommendations