Psychometrics versus Representational Theory of Measurement

Vessonen, Elina

doi:10.1177/0048393117705299

Cited by 10 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But philosophers are now getting up to speed, perhaps motivated by growing interest in general philosophy of measurement (Cartwright, Bradburn, & Fuller, ; Heilmann, ; Tal, ). By 2019, we have a handful of philosophical analyses of psychometrics in the science of well‐being (Alexandrova, , ; Angner, ), interpretations of psychometrics in terms of the realism/anti‐realism dichotomy (Hood, ), comparisons of psychometrics and the representational theory of measurement (Angner, ; but see also Suppes & Zinnes, ; Vessonen, , ), studies of the role of modelling in psychometrics (McClimans, Browne, & Cano, ; Peterson, ), and more general analyses of psychometrics as an epistemic activity (Alexandrova & Haybron, ).…”

Section: Introductionmentioning

confidence: 99%

Operationalism and realism in psychometrics

Vessonen

2019

Philosophy Compass

Self Cite

View full text Add to dashboard Cite

Psychometrics is one of the main approaches to social scientific measurement. It is relied upon in drug testing, economic policymaking, recruitment, and other decision‐making contexts. The first aim of this article is to introduce philosophers to key aspects of psychometrics, namely, classical test theory, item response theory, and construct validity. The second aim is to show how a debate on the nature of psychological attributes manifests in psychometrics. In this debate, realists claim that psychometric measures are indicators of independently existing qualities, while operationalists argue that a measure defines its target attribute. The third and final aim is to argue that despite its poor reputation among philosophers, operationalism is a viable approach to psychometrics.

show abstract

Section: Introductionmentioning

confidence: 99%

Operationalism and realism in psychometrics

Vessonen

2019

Philosophy Compass

Self Cite

View full text Add to dashboard Cite

show abstract

“…This idea is basic to representational theory of measurement (RTM; Krantz, Luce, Tversky, & Suppes, 1971). It formalizes axiomatic conditions by which empirical relational structures can be mapped to symbolic relational (data) structures ( representation theorem ), including permissible ways for transforming the latter without breaking their mapping onto the former ( uniqueness theorem ; Kyngdon, 2008a; Narens, 2002; Vessonen, 2017). But RTM stipulates neither theoretical concepts nor procedures for how and why any given empirical property could be mapped to a symbolic relational system, and many of its notions remain vague (Borsboom & Scholten, 2008; Mari et al, 2017).…”

Section: Measurement: Most Basic Concepts Principles and Processesmentioning

confidence: 99%

Psychometrics is not measurement: Unraveling a fundamental misconception in quantitative psychology and the complex network of its underlying fallacies.

Uher

2021

Journal of Theoretical and Philosophical Psychology

View full text Add to dashboard Cite

Psychometrics has always been confronted with fundamental criticism, highlighting serious insufficiencies and fallacies. Many fallacies persist, however, because each critic explores only some fallacies while still building on others. This article scrutinizes the epistemological, metatheoretical and methodological foundations of psychometrics, revealing a complex network of numerous conceptual fallacies underlying its framework of theory and practice. At its core lies a key challenge for psychology: the necessity to distinguish the phenomena under study from the means used to explore them (e.g., concepts, methods, data). This distinction is intricate because concepts constitute psychical phenomena in themselves and many psychical phenomena are accessible only through language-based methods. The analyses show how insufficient consideration of this important distinction and common misconceptions about concepts and language (e.g., signifier-referent conflation; reification of constructs) led to conflations of disparate notions of key terms in psychological measurement (e.g., 'variables', 'attributes', 'causality') and numerous interrelated fallacies (e.g., construct-referent conflation, phenomenon-quality-quantity conflation, numeral-number conflation). These fallacies are maintained and masked by repeated conceptual back-and-forth switching between two incompatible epistemological frameworks, 1) an operationist framework of data modelling implemented through methodical and statistical operations and 2) a realist framework of measurement sporadically invoked in theoretical considerations but neither theoretically elaborated nor empirically implemented. The analyses demonstrate that psychometrics constitutes only data modelling but not data generation or even measurement as often assumed and that analogies to (indirect or fundamental) physical measurement are mistaken. They provide theoretical support for the increasing criticism of psychometrics and its use in research and applied contexts.

show abstract

“…For measurement, these many-to-one mappings (homo- or isomorphisms) must be performed such that the study phenomena’s properties and their interrelations are appropriately represented by the properties and interrelations of the signs used as data ( representation theorem ). Permissible transformations specify how the numerical representations can be further transformed without breaking the mapping between the empirical relations under study and the numerical ones generated ( uniqueness theorem ; Figure 5; Vessonen, 2017).…”

Section: Measurement and Quantification Across The Sciencesmentioning

confidence: 99%

“…Another problem concerns establishing measurability (i.e., evidence of ordered additive structures of the same quality) because not just any mapping of numbers onto empirical relational structures constitutes measurement. But the appropriateness of particular numerical representations is often only assumed rather than established, thereby reducing the interpretability of the generated symbolic representation regarding the empirical phenomena under study (Blanton and Jaccard, 2006; Vessonen, 2017).…”

Section: Measurement and Quantification Across The Sciencesmentioning

confidence: 99%

Quantitative Data From Rating Scales: An Epistemological and Methodological Enquiry

Uher

2018

Front. Psychol.

115

View full text Add to dashboard Cite

Rating scales are popular methods for generating quantitative data directly by persons rather than automated technologies. But scholars increasingly challenge their foundations. This article contributes epistemological and methodological analyses of the processes involved in person-generated quantification. They are crucial for measurement because data analyses can reveal information about study phenomena only if relevant properties were encoded systematically in the data. The Transdisciplinary Philosophy-of-Science Paradigm for Research on Individuals (TPS-Paradigm) is applied to explore psychological and social-science concepts of measurement and quantification, including representational measurement theory, psychometric theories and their precursors in psychophysics. These are compared to theories from metrology specifying object-dependence of measurement processes and subject-independence of outcomes as key criteria, which allow tracing data to the instances measured and the ways they were quantified. Separate histories notwithstanding, the article’s basic premise is that general principles of scientific measurement and quantification should apply to all sciences. It elaborates principles by which these metrological criteria can be implemented also in psychology and social sciences, while considering their research objects’ peculiarities. Application of these principles is illustrated by quantifications of individual-specific behaviors (‘personality’). The demands rating methods impose on data-generating persons are deconstructed and compared with the demands involved in other quantitative methods (e.g., ethological observations). These analyses highlight problematic requirements for raters. Rating methods sufficiently specify neither the empirical study phenomena nor the symbolic systems used as data nor rules of assignment between them. Instead, pronounced individual differences in raters’ interpretation and use of items and scales indicate considerable subjectivity in data generation. Together with recoding scale categories into numbers, this introduces a twofold break in the traceability of rating data, compromising interpretability of findings. These insights question common reliability and validity concepts for ratings and provide novel explanations for replicability problems. Specifically, rating methods standardize only data formats but not the actual data generation. Measurement requires data generation processes to be adapted to the study phenomena’s properties and the measurement-executing persons’ abilities and interpretations, rather than to numerical outcome formats facilitating statistical analyses. Researchers must finally investigate how people actually generate ratings to specify the representational systems underlying rating data.

show abstract

Psychometrics versus Representational Theory of Measurement

Cited by 10 publications

References 27 publications

Operationalism and realism in psychometrics

Operationalism and realism in psychometrics

Psychometrics is not measurement: Unraveling a fundamental misconception in quantitative psychology and the complex network of its underlying fallacies.

Quantitative Data From Rating Scales: An Epistemological and Methodological Enquiry

Contact Info

Product

Resources

About