Approximations for the Conditional Case

  • Joseph Glaz
  • Joseph Naus
  • Sylvan Wallenstein
Part of the Springer Series in Statistics book series (SSS)


There is, by now, a voluminous literature on approximations. We will highlight those approximations that are interesting from a methodological point of view and could be considered optimal relative to the effort involved. There are two basic approaches used. The methods of moments and product limit approximations are based on spacings, and the other methods are based on cell occupancy numbers. The approximations based on spacings are described in Sections 10.1–10.4, and those on cell occupancy numbers in Sections 10.5–10.7. In order of computational effort they might be ordered as:
  1. 1.

    Simple one parameter exponential approximation.

  2. 2.

    Crude approximation based on cell occupancy probabilities.

  3. 3.
    1. (a)

      Markov-type approximation based on cell occupancy numbers.

    2. (b)

      Product limit approximations.

    3. (c)

      Method of moments: two-parameter approximations.

  4. 4.

    Average of upper and lower bounds based on three-way intersections.



Moment Approximation Unconditional Probability Nonoverlapping Cluster Matching Distribution Product Limit Approximation 
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.

Copyright information

© Springer Science+Business Media New York 2001

Authors and Affiliations

  • Joseph Glaz
    • 1
  • Joseph Naus
    • 2
  • Sylvan Wallenstein
    • 3
  1. 1.Department of Statistics The College of Liberal Arts and SciencesUniversity of ConnecticutStorrsUSA
  2. 2.Department of Statistics RutgersThe State University of New JerseyPiscatawayUSA
  3. 3.Department of Biomathematical SciencesMount Sinai School of MedicineNew YorkUSA

Personalised recommendations