Test Validity: A Matter of Consequence

By S. Messick. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Social Sciences & Humanities

Citations in the corpus

Measurement and Fairness (2019, background): “Downstream consequences are not only a normative concern, but fundamentally an aspect of validity: how these measurements are used may affect how they are interpreted and used in the future [44, 45].”
The concept of validity. (2004, background): “In the writings of leading theorists (i.e., Cronbach, 1988; Kane, 2001; Messick, 1981, 1989, 1998; Shepard, 1993), one will not find much that sustains it; rather, one is likely to find this type of idea in a discussion of historical conceptions of validity (Kane, 2001, pp. 319 –323).”
Current Concerns in Validity Theory (2001, background): “(pp. 293-294) But they went on to say that the "network still gives the constructs whatever meaning they do have" (p. 294).”
Toward a Unified Validation Framework in Mixed Methods Research (2007, methodology): “…by discourse and language in a community of researchers (Cherryholmes, 1988) and the subsequent weight of the research in the negotiations of data meaning; and (d) construct validation is a nonending, continuous, time- and context-specific, open process (Markus, 1998; Messick, 1995, 1998).”
Do test design and uses influence test preparation? Testing a model of washback with Structural Equation Modeling (2013, background): “For example, Pintrich (1999) reports standardized regression coefficients from extrinsic goals to use of cognitive strategies (from −.”
The role of auxiliary assumptions for the validity of manipulations and measures (2012, background): “Alternatively, Messick (1989, 1998) defined validity as the degree to which using the measures of concern produce correct conclusions or positive social outcomes.”
Comparing the Construct and Criterion-Related Validity of Ability-Based and Mixed-Model Measures of Emotional Intelligence (2005, background): “…validity of a test can be examined through several methods: by investigating its factor structure, by assessing its convergent validity, by assessing the extent to which it differentiates among groups, and by assessing its discriminant validity (Messick, 1981, 1998; Nunnally & Bernstein, 1994).”
Validating test score meaning and defending test score use: different aims, different methods (2016, background): “The unitary view centres on the extent to which available evidence supports interpretations of scores to re ﬂ ect standing with respect to a speci ﬁ ed construct (Cizek, 2012; Messick, 1998).”
Validity and the Consequences of Test Interpretation and Use (2011, background): “Like Messick (1998), we envision this network as a fundamental aspect of the science of measurement that provides a ‘‘framework for deriving empirically testable consequences of construct theory and a foil for framing plausible rival hypotheses to challenge construct meaning’’ (p. 40).”
Assessing statistical aspects of test fairness with structural equation modelling (2013, background): “Messick (1998) referred to these facets as, respectively, the consequential aspect versus the evidential aspect of test outcomes.”
Student engagement as a function of environmental complexity in high school classrooms (2016, methodology): “The Rasch analysis yielded ample preliminary evidence of the validity of the OLE-OLA measures (Messick, 1998).”