Just out - an article and a rejoinder: powerful stuff.
Humphry, S. (2017). Psychological measurement: Theory, paradoxes, and prototypes. Theory and Psychology, 27, 3, 407-418.
Abstract
The article focuses on the ongoing debate regarding the measurement of psychological attributes. The aim is to clarify different uses of the term theory and key points of agreement and disagreement among participants. In addition, the article addresses misinterpretations of key points in recent articles and notes an apparent paradox arising in the representational theory of measurement. Substantive theory is contrasted with both item response theory and the representational theory of measurement. Emphasis is placed on the direct dependence of the measurement of physical attributes on substantive quantitative theory as opposed to any form of separate measurement theory. It is concluded that the primary challenge faced in quantitative psychology is to posit testable substantive theories or laws which form a foundation for measurement.
And a response from Joel Michell:
Michell, J. (2017). On substandard substantive theory and axing axioms of measurement: A response to Humphry. Theory and Psychology, 27, 3, 419-425.
Abstract
My response to Humphry begins with some reflections upon why it is that after more than a century, psychometrics still lacks plausible substantive theories underwriting its claims to measure mental attributes and I explore the possibility that it is more myth-based technology than science. Historically, psychometrics has lacked any interest in coming to grips scientifically with the logical commitments of the presumption, implicit in the theories it does have (e.g., its Item Response Theories), that the attributes it aspires to measure are continuous quantities. This lack of interest might also explain Humphry’s misunderstanding of what is involved in the measurement theory axiom of continuity and his curious claim to have located a paradox therein. However, his attempt to rule the entire corpus of measurement theory as irrelevant to the enterprise of constructing and investigating substantive, psychometric theories betrays a failure to recognise that the form of substantive, quantitative theories also raises issues requiring empirical investigation.
I’m in total agreement with Joel here - the proposed ‘paradox’ from Stephen is plain silly. A kind of “nice-try but no bananas” line of argument!
However, the attempt to propose a paradox was inventive but in the end, simply misguided. But far more intellectually stimulating reading something like this than some routine piece of academic wallpaper involving imprecise/largely inaccurate descriptive moderation-mediation models or some other faddish latent variable/path-analysis claptrap.
I particularly like these two paragrpahs from Michell’s article:
“While psychometrics as a science would profit from investigations into the character of the attributes assessed; psychometrics as a technology might lose, for such investigations would expose the nakedness of the claim that tests measure and thereby threaten their standing in the market place. That is, psychometrics, as a myth-based technology, has a disincentive to pursue productive research into substantive theories of the attributes assessed by tests.
The cause of this disincentive is the fact that psychometricians committed themselves to the presupposition that the attributes tests assess are quantitative without reading the fine print entailed by this commitment. There is no evidence that any of the founding fathers of psychometrics (with the exception of Binet) understood the implications of committing themselves to quantitative structure. There was opportunity to do this, for a set of axioms of measurement was published (Hölder, 1901) immediately prior to publication of the first psychometric tests. The history of psychometrics illustrates the sad fact that those who aspire to extend the reach of quantitative science ignorant of quantitative structure are as well prepared for their venture as surgeons ignorant of anatomical structure would be for theirs.” p. 421.
In a sense, a sad testament to the embarrassing state of academic psychology as an investigative science.
Still, many academic psychologists won’t even read this work, let alone possess the scientific integrity, intellectual courage, and creativity to act upon it.
Regards .. Paul
Chief Research Scientist
Cognadev.com
__________________________________________________________________________________
M: +64-(0)21-415625