About Q methodology

Q methodology does not measure opinion. It maps patterns of viewpoints – the perspective types that exist in a group, not how many hold each one.

What Q methodology is

Q methodology was developed by William Stephenson in 1935 as a way to study subjectivity quantitatively. Each participant sorts a set of statements from "least agree" to "most agree" according to their own view. The result is an individual profile – a Q-sort – that expresses the person's standpoint.

When several people have completed the same sort, the Q-sorts are compared through factor analysis. The result is not groups of people but groups of perspectives: the ways of seeing the question that recur across the material.

Forced distribution

In a Q-sort the participant may not place any number of statements at the extremes. The distribution is forced – a classic bell curve from "least agree" (-4) to "most agree" (+4), with most statements in the middle and few at the edges.

This forces prioritisation. Instead of agreeing with everything, the participant has to pick which statements actually matter most. That prioritisation – not the statements themselves – is what makes patterns identifiable.

How it works, step by step

1. Rough sort. The participant reads each statement and picks whether it agrees, is neutral or disagrees. No prioritisation yet.
2. Fine sort. Statements from the agree and disagree piles are placed into the grid according to the forced distribution. Prioritisation happens here.
3. Comments on extremes. For the most extreme placements (+4/-4) the participant can write a short rationale. Used as qualitative support for factor interpretation.
4. Background questions. Organisation type and role. Used only in aggregate – never to identify individuals.

From individual sorts to perspective types

Once sorts are collected, factor analysis is run (typically principal component analysis with varimax rotation). Each factor represents a recurring perspective – a way of prioritising the statements that several participants share.

The end product is factor descriptions: "Perspective 1 values X and Y highly but Z low." These descriptions, plus participants' own comments on the extreme placements, form the workshop input.

How many participants are needed?

Q methodology requires substantially fewer participants than traditional surveys. This is because the method does not measure distributions in a population but maps perspective types. Each factor needs about 4–5 participants with strong loadings to stabilise, and a typical Q-study finds 3–5 factors.

Watts and Stenner (2012) recommend P ≈ Q/2 to Q, where Q is the number of statements. For this study (50 statements) that means:

• Minimum for exploratory analysis: around 15–20 participants
• Publication-quality: 25–40 participants
• Optimal stability: 40–60 participants

For comparison: STRATEGIOS' earlier Q-study PERSPECTIVES (perspectives on digitalisation, n=32) produced three clear factors. Doubling the participant count mainly increases reliability within each factor – not necessarily the number of perspective types.

What Q methodology is not

It is not an opinion poll, not a Likert scale and not a ranking exercise. It is a mapping of perspective types. "How many agree with X?" is an R-method question (traditional survey). "What ways of viewing X exist?" is the Q-method question.

References

Methodological foundations

• Stephenson, W. (1953). The Study of Behavior: Q-technique and its Methodology. University of Chicago Press.
• Brown, S. R. (1980). Political Subjectivity: Applications of Q Methodology in Political Science. Yale University Press.
• Brown, S. R. (1996). Q methodology and qualitative research. Qualitative Health Research, 6(4), 561–567.
• Watts, S., & Stenner, P. (2005). Doing Q methodology: theory, method and interpretation. Qualitative Research in Psychology, 2(1), 67–91.
• Watts, S., & Stenner, P. (2012). Doing Q Methodological Research: Theory, Method and Interpretation. Sage.
• McKeown, B., & Thomas, D. B. (2013). Q Methodology (2nd ed.). Sage.

Applied Q methodology in public administration and governance

• Selden, S. C., Brewer, G. A., & Brudney, J. L. (1999). Reconciling competing values in public administration: Understanding the administrative role concept. Administration & Society, 31(2), 171–204.
• Molenveld, A. (2020). Using Q methodology in comparative policy analysis. In Handbook of Research Methods and Applications in Comparative Policy Analysis.
• Kim, M. H., Kim, K., & Peters, B. G. (2025). Perceiving policy entrepreneurship: A Q-methodology study on the attitudes of mid-level managers in developing countries. Public Policy and Administration.
• Chaaban, Y., Sawalhi, R., & Lundberg, A. (2025). Middle leaders' sensemaking of their leadership practices in response to educational disruption: A Q-methodology study. Educational Management Administration & Leadership.
• Sarkar, A., & Traubinger, T. (2021). IS resilience decision priorities at German SMEs: A Q-method approach.
• Zuiderwijk, A., Volten, C., Kroesen, M., & Gill, M. Motivation perspectives on opening up municipality data: Does municipality size matter? Information.

Analysis tools

• Banasick, S. (2019). Ken-Q Analysis (version 1.0.6). Journal of Open Source Software, 4(36), 1360.