Evaluating validity evidence for instruments in statistics education
Abstract
This Breakout Session will focus on evaluating validity evidence supporting the interpretation of scores from instruments. While specific instruments will be used as examples, this session aims to build skills for assessing validity evidence in general. The contemporary view of validity evidence is both broader and deeper than ‘an instrument measuring what it is supposed to measure.’ However, statistics education is rife with incomplete views surrounding the development and use of instruments, and the result is a myriad of interpretations and conclusions that are not supported by appropriate evidence.
This Breakout Session will focus on supporting the audience in critically evaluating validity evidence supporting the use of statistics education instruments as reported in the literature. As part of this evaluation of validity evidence, attention will be given to how a lack of evidence threatens interpretations and conclusions as well as how this can be addressed.
