Start by naming the present status
The current Machiavelli DISC inventory contains 100 original self-report statements, a transparent scoring approach, and a six-page developmental report. It is research-informed and has not yet undergone independent psychometric validation or norming. The studies discussed throughout this library explain measurement principles; they do not report results for our questionnaire. No numerical reliability, validity, fairness, or predictive-performance claim should be inferred from their presence here. The roadmap below describes proposed work, not completed studies.
Flake and Fried’s discussion of questionable measurement practices emphasizes transparent definitions, instrument details, scoring choices, and evidence. Their argument is useful for a product because unreported changes can make seemingly similar scores difficult to evaluate. Our proposed response is a versioned technical record: the intended population, construct definitions, item set, instructions, response options, scoring rules, report logic, and reasons for revisions should be documented together.
Design studies before celebrating findings
Nosek and colleagues describe preregistration as a way to distinguish predictions made before observing outcomes from explanations developed afterward. Both exploratory and confirmatory analyses can be useful, but they answer different questions. For this inventory, a preregistered study should state its key hypotheses, exclusion rules, primary analyses, and interpretation criteria. Unexpected findings can guide improvements while remaining clearly identified as exploratory.
The first proposed phase is qualitative: independent content review and cognitive interviews with adults from the intended user population. The next phase pilots the questionnaire, examines comprehension and response distributions, and explores candidate structures. A revised version would then be evaluated in new data. We should not repeatedly modify the model on one dataset and describe its eventual fit as independent confirmation. Negative and mixed results belong in the record alongside supportive findings.
Match the sample to the question
Lakens’s account of sample-size justification distinguishes approaches based on power, desired precision, population coverage, resources, and other explicit considerations. It cautions against allowing an unexplained number to stand in for a research design. Our proposed studies should justify their sample sizes for the particular model, desired uncertainty, and comparisons. There is no universal participant count that certifies a 100-item inventory as validated.
Recruitment should describe who participated, how they were approached, the language used, and who is underrepresented. Structural evaluation, retest work, external associations, and group comparability may require different designs or samples. A future normative reference group would need a defined population and a transparent sampling account. A large convenience sample should not silently become a claim about every adult, every occupation, or every country.
Publish the boundary of each conclusion
A proposed technical release would report what was tested, what was found, the uncertainty, and the practical limits. It should identify which inventory version the evidence concerns and whether scoring or report language changed afterward. Where data sharing is appropriate, privacy-preserving materials and reproducible analysis code can support scrutiny. Independent replication and review would strengthen the evidence; their status must be stated accurately rather than implied through a badge or marketing phrase.
Future assessments require their own programme. Big Five, Dark Triad, 16PF, and HEXACO describe different theoretical or measurement traditions, and adding a new title to the catalogue cannot transfer evidence from DISC. Any future instrument needs an appropriate rights review where relevant, its own construct definitions, development process, validation evidence, and stated uses. Our long-term standard is simple: readers should be able to tell the difference between an idea, an implemented feature, a completed study, and a supported conclusion.
SOURCES & FURTHER READING
Flake, J. K., & Fried, E. I. (2020). Measurement schmeasurement: Questionable measurement practices and how to avoid them. Advances in Methods and Practices in Psychological Science, 3, 456–465. ↗Nosek, B. A., Ebersole, C. R., DeHaven, A. C., & Mellor, D. T. (2018). The preregistration revolution. Proceedings of the National Academy of Sciences, 115, 2600–2606. ↗Lakens, D. (2022). Sample size justification. Collabra: Psychology, 8, 33267. ↗