Hacker News Reader

Comment by game_the0ry | Hacker News Reader

> Through field observations (N=13) and qualitative surveys (N=99)...

Not a statistically significant sample size.

This is a qualitative methods paper, so statistical significance is not relevant. The rough qualitative equivalent would instead be "data saturation" (responses generally look like ones you've received already) and "thematic saturation" (you've likely found all the themes you will find through this method of data collection). There's an intuitive quality to determining the number of responses needed based on the topic and research questions, but this looks to me like they have achieved sufficient thematic saturation based on the results.

So, I upvoted your comment bc I genuinely believe there is something in your comments worth learning from, but...

> This is a qualitative methods paper, so statistical significance is not relevant.

I have never heard of a "qualitative methods paper" and it sounds like something a researcher would do to push a narrative with "qualitative data" rather than data that could be measured.

Tell me why I am wrong.

You're not necessarily wrong, but the phrase "push a narrative," the scare quotes around "qualitative data," and your initial comment suggest to me that you are not familiar with qualitative research but have a bias or mistrust against it (no judgment, just stating my observation). If you would like to know more about it, this[1] provides a reasonable overview, and if you would like to know much more, I can ask my spouse, who is a qualitative methodologist in medicine at an R1[2], for her recommendations. I can also tell you what I think of this specific paper, but I did not want it to color my initial comment.

[1] https://en.wikipedia.org/wiki/Qualitative_research

[2] https://en.wikipedia.org/wiki/List_of_research_universities_...

> your initial comment suggest to me that you are not familiar with qualitative research but have a bias or mistrust against it

I can confirm that, yes, I do have an arguably paranoid bias and/or mistrust against information that is not quantifiable in nature nor is simple enough for me (an idiot) to understand easily.

Appreciate the thoughtful response. Don't ask the spouse, just enjoy the new year. I'll figure it out.

97 samples is enough to get a 95% confidence level if you accept a 10% margin of error. 99 is not so bad, at least.

https://www.surveymonkey.com/mp/sample-size-calculator/

Significance depends on effect size.

How many independent witnesses would you need to convict someone of murder?

Same thoughts exactly.

Reply on news.ycombinator.com