JSM 2004 - Toronto

Abstract #301626

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2004 Program page
Activity Number: 226
Type: Contributed
Date/Time: Tuesday, August 10, 2004 : 10:30 AM to 12:20 PM
Sponsor: Biometrics Section
Abstract - #301626
Title: Rethinking the Adjustment for Chance in Agreement Coefficients
Author(s): Michael P. Fay*+
Companies: National Institute of Allergy and Infectious Diseases
Address: 6700A Rockledge Dr., Bethesda, MD, ,
Keywords: concordance correlation coefficient ; kappa ; reliability ; weighted kappa
Abstract:

We study the measurement of agreement or reliability between two different instruments. In the standard agreement coefficients (e.g., Kappa, weighted Kappa, concordance correlation coefficient) chance agreement is modeled using expected agreement between two independent random variables (RVs) each distributed according to the marginal distribution of one of the instruments. We propose that the adjustment for chance should also be modeled by expected agreement between two independent random variables, except that both RVs should be identically defined by the mixture distribution of the two marginal distributions. The advantage of the proposed adjustment for chance is that differences between the two marginal distributions will not induce greater apparent agreement. We call the proposed coefficients random marginal agreement coefficients (RMAC). An important RMAC may be estimated by the intraclass kappa, which has previously been proposed to measure agreement for nominal data. For ordinal and continuous data, the RMAC are new (to the best of our knowledge) and may provide more appropriate alternatives to the weighted kappa and concordance correlation coefficient.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2004 program

JSM 2004 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2004