What Kind of Thing Is Your Construct: Reflective, Formative, or Fiction?

Jonathan R. Brauer, Jacob C. Day and Amanda Graham
Additional contact information
Amanda Graham: Georgia Southern University

No 5hwgv_v2, SocArXiv from Center for Open Science

Abstract: What kind of thing is your construct? We rarely ask, even while certifying its measures reliable and predictive. Measurement theory gives three structurally distinct answers: reflective, a real entity generating interchangeable indicators; formative, an emergent composite of distinct components; and measurement fiction, a label for correlated phenomena with no unified cause. Socioeconomic status, collective efficacy, and social capital, among others, could be any of the three, because all three can produce comparable aggregate signatures (adequate loadings, good fit, significant prediction); the standard validation toolkit, built to assume reflective structure, cannot reliably tell which. We interrogate that assumption at escalating stringency on self-control across 30 countries (ISRD-2), culminating in a predictive concordance test of whether supposedly interchangeable items identify the same individuals. Evidence rules out a unidimensional reflective trait yet cannot separate formative from fiction. We offer a three-question diagnostic and four research designs to avoid reifying indices as unified traits.

Date: 2026-07-13
References: Add references at CitEc
Citations:

Downloads: (external link)
https://osf.io/download/6a53edc1c102db2aec7afc34/

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:osf:socarx:5hwgv_v2

DOI: 10.31219/osf.io/5hwgv_v2

Access Statistics for this paper

More papers in SocArXiv from Center for Open Science
Bibliographic data for series maintained by OSF ().