this post was submitted on 14 Aug 2023
309 points (97.0% liked)
Technology
60082 readers
3879 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Sample size, 50 students. Lol nothing to see here. This has no value whatsoever.
This is such a common sneer, but it's naive and misguided. In the hope a few people see this, consider a thought experiment: how many students would you have to push off a cliff to get solid evidence that pushing people off a cliff is harmful? The point being that when a phenomenon is powerful, it's quite possible to study it even with small and selective samples.
I get what you mean but please read the study: https://link.springer.com/article/10.1007/s41347-023-00304-7
They themselves note that the very small sample size would be an issue. They say they would need 78 people for even remotely confident results, then they initially targeted 74 people, of which 20 dropped out.
Let me be clear that I too want to believe that social networks are bad for people, but studies like this one do very very little to provide any meaningful data to base my opinion on.
It's good to look at the original study, but what that tells me is that for the effect to emerge as significant despite the lack of participants, it was quite possibly even larger than the researchers estimated in their power analysis
Maybe a motivation to do a bigger one
Small sample sizes don't invalidate studies. They reduce the statistical certainty, but can still be accurate and there's formulas for gauging how accurate a given sample size is based off the standard deviation.
The student only part does mean a sampling biase, but that doesn't invalidate things either. Mostly just limits it such that we can only make the claim for students and not anyone else (but it's still a meaningful result and provides justification for larger studies).
Nonsense. Small sample size studies are legitimate, there is just an increased margin of error when generalizing to the population. They can absolutely still be significant.