This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/68972
Description
Title
Techniques for Assessing the Quality of Ratings
Author(s)
Burns, Mary Daugherty
Issue Date
1985
Department of Study
Education
Discipline
Education
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Education, Tests and Measurements
Abstract
This thesis identified and studied nine analytical techniques used to compute individual rater reliability estimates. These techniques were analyzed to compare reliability estimates, to assess validity, and to determine the effects achieved by modifying the underlying distribution.
To study these analytical techniques, two categories of data were analyzed. The first category consisted of simulated rating data such that individual rater reliabilities were predetermined to serve as the criterion and the underlying distribution was predetermined. Data were simulated for three underlying distributions, normal, bimodal, and negatively skewed. The second category consisted of empirical rating data for "novice" raters and for "expert" raters who served as the criterion.
Analyses of the simulated rating data indicated that the individual rater reliability estimates, computed by each analytical technique, were not comparable to the simulated reliabilities for each rater. This was true regardless of the underlying distribution. The underlying distribution affected the magnitude of the individual rater reliability estimates and the agreement between each analytical technique and the criterion. Generally, the analytical techniques were more in agreement with one another than any one technique was in agreement with the criterion. In terms of rank ordering raters, none of the analytical techniques ranked the raters identically to the predetermined simulation. However, all the techniques, regardless of the underlying distribution were able to identify the two most reliable raters, but were unable to identify the rater with the lowest reliability.
Due to the limited reliability achieved by the "expert" rater criterion, no conclusion was drawn regarding the validity of the individual rater reliability techniques as applied to the empirical rating data.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.