Reference table
Purposive sample size by sampling type
A quick reference for qualitative sample sizes under purposive sampling. It gives a starting number of participants for criterion, homogeneous, maximum variation and snowball sampling, plus the practical rule of planning 8 to 12 interviews and checking for saturation partway through. Use it when you scope a user interview study, then let new themes, not the plan, decide when you stop.
Where this appears
What's in this reference table
| Sampling type | Participants | What it rests on |
|---|---|---|
| Criterion | 6 to 12 per segment | Usually enough to reach thematic saturation |
| Homogeneous | 6 to 12 per segment | Usually enough to reach thematic saturation |
| Maximum variation | 12 to 20 | Enough to cover each dimension of variation |
| Snowball | Until saturation | As few as 8 in a tight network, 30+ in a diverse one |
| Any type, to start | 8 to 12 | Review after 5 or 6. Stop when 3 in a row add only small nuances |
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/purposive-sample-size-by-sampling-type"><img src="https://www.koji.so/visuals/purposive-sample-size-by-sampling-type/purposive-sample-size-by-sampling-type.png" alt="Table of how many participants each type of purposive sampling needs, from 6 to 12 per segment for criterion sampling to 12 to 20 for maximum variation." width="1200" height="745" /></a>
<p>Source: <a href="https://www.koji.so/visuals/purposive-sample-size-by-sampling-type">Purposive sample size by sampling type</a>, Koji</p>
