Suggestions for Rethinking Validation

摘要

The paper by Maul raises issues of validity in survey-based measurement that deserve far wider consideration and scrutiny than they typically receive. If the paper would lead to the kinds of rethinking proposed by the author simply in the terms in which he presents them, that alone would be a very positive consequence. MauΓs demonstration that reliability coefficients are not measures of the internal consistency or unidimensionality of an instrument accords exactly with theory, for instance, but remains widely unacknowledged in research and practice (Green, Lissitz, & Mulaik, 1977; Hattie, 1985; Sijtsma, 2009). That said, given this opportunity to expand on or take issue with some of the points raised in the article, I would like to offer some alternative paths for rethinking validation processes in survey research.