Access

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

If You Use a Screen Reader

This content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.

Methodology and Algorithms of Empirical Likelihood

Peter Hall and Barbara La Scala
International Statistical Review / Revue Internationale de Statistique
Vol. 58, No. 2 (Aug., 1990), pp. 109-127
DOI: 10.2307/1403462
Stable URL: http://www.jstor.org/stable/1403462
Page Count: 19
  • Read Online (Free)
  • Download ($12.00)
  • Subscribe ($19.50)
  • Cite this Item
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Methodology and Algorithms of Empirical Likelihood
Preview not available

Abstract

We describe the main features of empirical likelihood and discuss recent developments, including Bartlett correction and location adjustment. Algorithms are provided for implementing empirical likelihood in important cases, for example to means, variances and correlation coefficients. It is shown that empirical likelihood is a serious competitor with contemporary methods such as the bootstrap. Indeed empirical likelihood has several advantages, in that it does not impose prior constraints on region shape, does not require construction of a pivotal statistic, and admits a Bartlett correction which allows very low coverage error. Empirical likelihood deserves a prominent place in the modern statistician's armoury of computer-intensive tools. /// Nous décrivons les traits principaux de la méthode de vraisemblance empirique et discutons les développements récents, incluant la correction de Bartlett et l'ajustement de location. Nous donnons des algorithmes pour la méthode de vraisemblance empirique dans certains cas importants, par exemple pour les moyennes, les variances et les coefficients de corrélations. On démontre que la méthode de vraisemblance empirique est une concurrente sérieuse comparée à d'autres méthodes contemporaines comme l'auto-amorcage. D'ailleurs, la méthode de vraisemblance empirique a plusieurs avantages. Elle n'impose pas de constraintes préalables sur la forme de la région. Elle n'exige pas de construction de statistique pivotale et elle permet la correction de Bartlett qui donne une erreur de recouvrement très basse. La méthode de vraisemblance empirique mérite une place importante dans l'arsenal de techniques informatiquement intensive du statisticien moderne.

Page Thumbnails

  • Thumbnail: Page 
[109]
    [109]
  • Thumbnail: Page 
110
    110
  • Thumbnail: Page 
111
    111
  • Thumbnail: Page 
112
    112
  • Thumbnail: Page 
113
    113
  • Thumbnail: Page 
114
    114
  • Thumbnail: Page 
115
    115
  • Thumbnail: Page 
116
    116
  • Thumbnail: Page 
117
    117
  • Thumbnail: Page 
118
    118
  • Thumbnail: Page 
119
    119
  • Thumbnail: Page 
120
    120
  • Thumbnail: Page 
121
    121
  • Thumbnail: Page 
122
    122
  • Thumbnail: Page 
123
    123
  • Thumbnail: Page 
124
    124
  • Thumbnail: Page 
125
    125
  • Thumbnail: Page 
126
    126
  • Thumbnail: Page 
127
    127