ERIC Number: EJ1023628
Record Type: Journal
Publication Date: 2013
Reference Count: 2
What Is Essential in Standard Setting and Construct Maps? Commentary on Adam E. Wyse's "Construct Maps as a Foundation for Standard Setting"
Schulz, E. Matthew
Measurement: Interdisciplinary Research and Perspectives, v11 n4 p192-194 2013
In this article, E. Matthew Schulz responds to Adam Wyse's article, "Construct Maps as a Foundation for Standard Setting." In doing so, he asserts that one of the most important ideas in Wyse's work is that information used in standard setting needs to be better represented through the use of graphics. However, he's not sure that this is enough to make construct maps foundational to standard setting or what else there is or could be about construct maps that makes them foundational. In Schulz's opinion, if every construct map contained an item map at its core, he would consider construct maps foundational. He notes that the construct maps described by Wyse all seem to contain a scale of some sort, but it is not clear if there are any requirements for the scale used in construct maps, or what other elements the map absolutely should show. Schulz argues that: (1) the measurement scale in the map should be a linear transformation of the underlying IRT metric; and (2) the map should show information about conditional (on scale values) examinee response probabilities on test items. For ease of reference, these two requirements constitute an "item map" and in Schulz's view an item map should be an essential, indispensible component of a construct map. The item map is necessarily spatially representative since the scale is a linear transformation of the IRT metric. Incidentally, item maps are inherently part of the mapmark, not the Bookmark, method. The creators of Bookmark did not recognize the value of spatially representative item maps in their method. They used a simple list, or table, which they called an item map. Schulz contends that Wyse would more effectively advance construct maps, and their contribution to standard setting, if he developed more arguments in favor of what the construct map must include in order to be effective--and fewer arguments in other directions. In this article, Schulz expands on this viewpoint and evaluates a number of other elements noted in Wyse's article as they relate to the analysis of standard-setting issues.
Descriptors: Standard Setting (Scoring), Maps, Item Response Theory, Test Items, Methods, Performance, Standards
Psychology Press. Available from: Taylor & Francis, Ltd. 325 Chestnut Street Suite 800, Philadelphia, PA 19106. Tel: 800-354-1420; Fax: 215-625-2940; Web site: http://www.tandf.co.uk/journals
Publication Type: Journal Articles; Opinion Papers; Reports - Evaluative
Education Level: N/A
Authoring Institution: N/A