Sequential Construction of an Experimental Design from an I.I.D. Sequence of Experiments without Replacement

  • Luc Pronzato
Part of the Nonconvex Optimization and Its Applications book series (NOIA, volume 51)


We consider a regression problem, with observations y k = η(θ, ξ k ) + ϵ k , where {ϵ k } is an i.i.d. sequence of measurement errors and where the experimental conditions £& form an i.i.d. sequence of random variables, independent of {ϵ k }, which are observed sequentially. The length of the sequence {ξ k } is N but only n < N experiments can be performed. As soon as a new experiment ξ k is available, one must decide whether to perform it or not. The problem is to choose the n values \({\xi _{{k_1}}},.....{\xi _{{k_n}}}\) at which observations \({y_{{k_1}}},.....,{y_{{k_n}}}\) will be made in order to estimate the parameters θ. An optimal rule for the on-line selection of (math) is easily determined when p = dim θ = 1. A suboptimal open-loop feedback-optimal rule is suggested in Pronzato (1999b) for the case p > 1. We propose here a different suboptimal solution, based on a one-step-ahead optimal approach. A simple procedure, derived from an adaptive rule which is asymptotically optimal, Pronzato (1999a), when p = 1 (N → ∞, n fixed), is presented. The performances of these different strategies are compared on a simple example.


Sequential design random experiments expected determinant 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Embrechts, P., Klüppelberg, C. and Mikosch T. (1997). Modelling Extremal Events. Berlin: Springer-Verlag.zbMATHCrossRefGoogle Scholar
  2. Fedorov, V.V. (1972). Theory of Optimal Experiments. N.Y.: Academic Press.Google Scholar
  3. Fedorov, V.V. (1989). Optimal design with bounded density: optimization algorithms of the exchange type. JSPI 22, 1–13.zbMATHGoogle Scholar
  4. Feller, W. (1966). An Introduction to Probability Theory and Its Applications. N.Y.: Wiley.zbMATHGoogle Scholar
  5. Pronzato, L. (1998a). On a property of the expected value of a determinant. Statistics & Probability Letters 39, 161–165.MathSciNetzbMATHCrossRefGoogle Scholar
  6. Pronzato, L. (1998b). Optimal selection of information with restricted storage capacity. In Proc. ICASSP’98 4, pp. 2285–2288. Seattle.Google Scholar
  7. Pronzato, L. (1999a). Optimal and asymptotically optimal decision rules for sequential screening and resource allocation. Technical Report 99–19, Laboratoire I3S, CNRS-UPRES-A 6070, Sophia Antipolis, France, Scholar
  8. Pronzato, L. (1999b). Sequential selection of observations in randomly generated experiments. Tatra Mountains Math. Pub. 17, 167–175.MathSciNetzbMATHGoogle Scholar
  9. Wynn, H.P. (1970). The sequential generation of D-optimum experimental designs. Ann. Math. Stat. 41, 1655–1664.MathSciNetzbMATHCrossRefGoogle Scholar
  10. Wynn, H.P. (1982). Optimum submeasures with applications to finite population sampling. In Statistical Decision Theory and Related Topics III. Proc. 3rd Purdue Symp 2 (Eds S.S. Gupta and J.O. Berger), 485–495. N.Y.: Academic Press.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2001

Authors and Affiliations

  • Luc Pronzato
    • 1
  1. 1.Laboratoire I3SCNRS-UNSASophia-AntipolisFrance

Personalised recommendations