Methods

Construct validity

Construct validity concerns whether evidence supports interpreting a score as a measure of the proposed psychological construct. It involves a reasoned network of expectations about content, structure, relationships to other measures, and relevant group differences. An attractive label or a reliable score is insufficient.

Do observations support the interpretation we want to make from this score?

How it works

  1. State the proposed score interpretation and intended use. Identify the construct boundaries and the people and settings for which the claim is being made before looking for a convenient validation statistic.
  2. Form explicit predictions about relationships with related and distinct measures, and examine whether item content and score structure fit the concept. Select comparisons that could reveal a mistaken interpretation.
  3. Evaluate the pattern of evidence and credible alternative explanations. Report contradictions and population limitations, and seek new evidence when translating, adapting, or applying the measure for a different purpose.

Evidence: (COSMIN Manual, Version 2.0, n.d.); (Reliability and Validity of Measurement, n.d.)

Distinguishing belonging from sociability

Teaching scenario

Synthetic example: A team drafts a campus-belonging questionnaire. It predicts that belonging should relate to feeling supported, but asks whether items about attending many parties instead capture sociability or opportunity. Commuting students and students with caring responsibilities may feel connected without attending evening events. The team therefore reviews the item content with intended respondents and considers alternative wording before interpreting group comparisons. This is a proposed validity investigation with no invented correlation or group difference. Learners can identify what evidence would challenge, rather than merely confirm, the intended interpretation.

This example is constructed for learning. It does not report an observed research result.

What can you conclude?

Supports a bounded interpretation of scores when several relevant lines of evidence converge.

Evidence: (COSMIN Manual, Version 2.0, n.d.); (Reliability and Validity of Measurement, n.d.)

Limits and common mistakes

  • Validation is an ongoing argument about an interpretation and use, not a certificate that transfers unchanged across settings.
  • A predicted association can have several explanations; shared wording or shared method can imitate conceptual convergence.

A mistake to catch

Calling a scale valid because its items look sensible, or because one association reached statistical significance.

Evidence: (COSMIN Manual, Version 2.0, n.d.); (Reliability and Validity of Measurement, n.d.)

Sources and inspection notes

Links checked October 21, 2026. Inspection scope is stated for each source; an access date is not a publication date.

  1. COSMIN manual, version 2.0. (n.d.). https://www.cosmin.nl/wp-content/uploads/COSMIN-manual-V2_final.pdf

    Printed pages 12–14, taxonomy and Table 1.1 Official methods manual for patient-reported outcome measures. Its scope is PROMs; broader psychology applications here are explicit teaching adaptations. Opened and checked 21 October 2026.

  2. Reliability and validity of measurement. (n.d.). https://opentextbc.ca/researchmethods/chapter/reliability-and-validity-of-measurement/

    Test-Retest Reliability; Internal Consistency; Interrater Reliability; Content and Criterion Validity Original teaching chapter. Use distinctions, not its universal-looking coefficient cutoffs or oversimplified alpha explanation. Opened and checked 21 October 2026.

Keep reading

Spielman, R. M., Jenkins, W. J., & Lovett, M. D. (2020). Psychology 2e. OpenStax. https://openstax.org/books/psychology-2e/pages/2-3-analyzing-findings

Nearest related OpenStax Psychology 2e reading. This is a course connection, not evidence for every specialist detail above.

Specialist reading: Reliability and validity of measurement. (n.d.). https://opentextbc.ca/researchmethods/chapter/reliability-and-validity-of-measurement/

Related methods

Try the methods · Read a study · Explore psychological measures