Framework
Five levels for quantifying qualitative data
From whether a theme appeared to how it differs between segments
A five-level framework for counting in qualitative research. Presence asks whether a theme appeared, prevalence counts the participants who raised it, salience looks at how much it mattered to them, co-occurrence shows which themes appear together, and comparison looks across segments. Use it to decide which numbers a set of interviews can support. Koji counts themes by the number of interviews that mention them.
Where this appears
What's in this framework
- Presence: Did the theme come up at all, anywhere in the dataset?
- Prevalence: How many participants raised it, out of everyone you spoke to.
- Salience: How much it mattered: raised unprompted, repeated, or tied to a decision.
- Co-occurrence: Which themes turn up together in the same interviews.
- Comparison: Whether prevalence differs between segments. Needs the most care.
Use this image
Free to use in your docs, decks and posts under CC BY 4.0, as long as you credit Koji with a link to this page. To embed it, paste this into your page:
html
<a href="https://www.koji.so/visuals/quantifying-qualitative-data-five-levels"><img src="https://www.koji.so/visuals/quantifying-qualitative-data-five-levels/quantifying-qualitative-data-five-levels.png" alt="Framework showing five levels for quantifying qualitative data: presence, prevalence, salience, co-occurrence and comparison across segments." width="1080" height="1080" /></a>
<p>Source: <a href="https://www.koji.so/visuals/quantifying-qualitative-data-five-levels">Five levels for quantifying qualitative data</a>, Koji</p>
