If you need an accessible version of this item please contact JSTOR User Support

Improved Approximations for Multilevel Models with Binary Responses

Harvey Goldstein and Jon Rasbash
Journal of the Royal Statistical Society. Series A (Statistics in Society)
Vol. 159, No. 3 (1996), pp. 505-513
Published by: Wiley for the Royal Statistical Society
DOI: 10.2307/2983328
Stable URL: http://www.jstor.org/stable/2983328
Page Count: 9
  • Download PDF
  • Cite this Item

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 need an accessible version of this item please contact JSTOR User Support
Improved Approximations for Multilevel Models with Binary Responses
Preview not available

Abstract

This paper discusses the use of improved approximations for the estimation of generalized linear multilevel models where the response is a proportion. Simulation studies by Rodriguez and Goldman have shown that in extreme situations large biases can occur, most notably when the response is binary, the number of level 1 units per level 2 unit is small and the underlying random parameter values are large. An improved approximation is introduced which largely eliminates the biases in the situation described by Rodriguez and Goldman.

Page Thumbnails

  • Thumbnail: Page 
[505]
    [505]
  • Thumbnail: Page 
506
    506
  • Thumbnail: Page 
507
    507
  • Thumbnail: Page 
508
    508
  • Thumbnail: Page 
509
    509
  • Thumbnail: Page 
510
    510
  • Thumbnail: Page 
511
    511
  • Thumbnail: Page 
512
    512
  • Thumbnail: Page 
513
    513