Home

ISRT, University of Dhaka

Institute of Statistical Research and Training

Site Navigation

  • JSR
    • All Articles
    • Articles by Vol. No. Year
  • Training
  • Publications
    • MS Theses
  • Seminar
  • People
    • Alumni
    • All Faculty
    • Professor
    • Associate Professor
    • Assistant Professor
    • Lecturer
    • Supernumerary Professor
    • Former Faculty
    • Former Directors
Home
    • Home
    • News
    • Contact

Quick Links

Webmail Login
Students' Support Forum

Navigation

  • Create content
    • Alumni Profile

Is r* Linear in r?

 

D.A.S. Fraser, L. Faye, Y. Cai, K. Ji, M. Mallo, and R. Thinnyam (2008). Is r* Linear in r?. Journal of Statistical Research, Vol. 42, No. 2, pp.  7-19.

 

Abstract

The quantity $ r^*(\psi, y) $ was introduced by Barndorff-Nielsen, in part as a distributional refinement of the signed likelihood root $ r(\psi, y), $ a refinement that can also be approximated by a mean and standard deviation adjustment of the root $ r(\psi, y). $ We clarify: that $ r^* $ is not linear in $ r; $ that $ r^* $ achieves large distributional improvement on $ r(\psi, y); $ and that $ r^* $ provides the definitive separation of inference information concerning scalar component parameters of a statistical model. These distributional and inference properties deserve broader awareness.

 

Fulltext PDF not available for this article.

 

Information for

Prospective Students
Visitors
Parents or Guardians

Resources

List of Bangladeshi Universities
Statistics Departments (by country)
Statistical Journals

© 1999-2009, ISRT, University of Dhaka, Bangladesh
Site established: 22 June 1999