What is it about?

An example dataset is analyzed and the results used to demonstrate that a cross-grade (vertical) scale can be developed for an assessment for which the dimension being measured varies somewhat from grade to grade. The conclusion is reached that if a scaling model fits cross-grade data despite an assumption that somewhat different constructs are measured at each grade, valid interpretations of the cross-grade scale are appropriate.

Featured Image

Why is it important?

Many authors writing about the development of cross-grade scales have explicitly stated that such a scale is inappropriate because different constructs are measured at each grade level. This report demonstrates that this is not necessarily true.

Read the Original

This page is a summary of: Unidimensional Vertical Scaling in Multidimensional Space, ETS Research Report Series, July 2017, Wiley,
DOI: 10.1002/ets2.12157.
You can read the full text:

Read

Contributors

The following have contributed to this page