Cookies?
Library Header Image
LSE Research Online LSE Library Services

Quantitative psychology under scrutiny: measurement requires not result-dependent but traceable data generation

Uher, Jana (2021) Quantitative psychology under scrutiny: measurement requires not result-dependent but traceable data generation. Personality and Individual Differences, 170. ISSN 0191-8869

[img] Text (uher_2021b_quantitative psy under scrutiny_accepted-ms) - Accepted Version
Repository staff only until 9 October 2022.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (855kB) | Request a copy
Identification Number: 10.1016/j.paid.2020.110205

Abstract

Various lines of critique of quantitative psychology, well-established and new, are used to trace along the field's typical steps of research a complex network of misconceptions and fallacies codified in psychological jargon. The article explores what constructs actually are, why they are needed in psychology, fallacies and challenges in construct research, and the crucial role of language. It shows how common misconceptions of language and concepts mislead psychologists to conflate phenomena, qualities, quantities and constructs with one another and with their semiotic encodings in terms, variables and scores. The article clarifies the conceptual relations between nomological networks, representation theorems and psychometric modelling. It reveals conflations of disparate notions of causality and unobservability, and erroneous equations of nomological networks with semantic networks, description with explanation, and measurement theories with explanatory theories. Instead of establishing causal measurand-result relations, common practices match data generation to the results rather than the phenomena and properties studied. Mathematical meaning for scores is often created from differences between individuals and between different phenomena and properties, which constitute mere conceptual entities and cannot reflect magnitudes attributable to individuals. This entails biased inferences on the actual study phenomena and shows that replicability problems may be even larger than assumed.

Item Type: Article
Official URL: https://www.sciencedirect.com/journal/personality-...
Additional Information: © 2020 Elsevier Ltd
Divisions: Psychological and Behavioural Science
Subjects: B Philosophy. Psychology. Religion > BF Psychology
H Social Sciences > H Social Sciences (General)
Date Deposited: 24 Sep 2021 11:06
Last Modified: 20 Oct 2021 01:08
URI: http://eprints.lse.ac.uk/id/eprint/112131

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics