Premium
Rejoinder: Evaluating Standard Setting Methods Using Error Models Proposed by Schulz
Author(s) -
Reckase Mark D.
Publication year - 2006
Publication title -
educational measurement: issues and practice
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.158
H-Index - 52
eISSN - 1745-3992
pISSN - 0731-1745
DOI - 10.1111/j.1745-3992.2006.00062.x
Subject(s) - perspective (graphical) , standard error , computer science , range (aeronautics) , regression , statistics , psychology , machine learning , artificial intelligence , mathematics , materials science , composite material
Schulz (2006)provides a different perspective on standard setting than that provided in Reckase (2006) . He also suggests a modification to the bookmark procedure and some alternative models for errors in panelists' judgments than those provided by Reckase. This article provides a response to some of the points made by Schulz and reports some additional analyses of the bookmark and modified Angoff method using the suggestions made by Schulz. The results support considering a range of items when placing a bookmark using that method and they show that the regression of panelists' probability of correct response estimates toward .5 can have serious effects on the recovery of intended cut scores. The complexity of the standard setting processes, and the need for detailed descriptions of standard setting processes are also discussed.