Polls show Americans between the ages of 18 and 29 are more likely to agree that Israel is committing genocide in besieged Gaza than other age groups in the country.
According to the Economist/YouGov poll, roughly equal numbers of adults believe Israel’s military campaign against Palestinians, which is estimated to have killed more than 25,000 people since 7 October, amounts to genocide: 35% say it is, 36% say it isn’t, with 29% undecided.
Among younger Americans, and along political lines, divisions are more prominent. Almost half of those surveyed aged 18-29, 49%, say Israel is committing genocide, with 24% disagreeing and 27% uncertain
I wouldn’t call myself a master at stats, but maybe learned since I use stats daily as a data engineer. This is called the Small Sample Fallacy and suffers self selection bias (as in, samples are choosing on their own to take the survey).
People who commit the small sample fallacy can be said to assume that a small random sample should be as reliable as, and as regular as, a large random sample, but not too regular.
You put in the wrong numbers, the margin of error is lower, but that’s a moot point because it falls into fallacy.
These are they same fallacies that lead to “every” 2016 election poll saying Hillary was going to win… We all know how that went.
*Surveys 100 people in one place*
“Yup, this is a representation of the opinion of ~60 million young people across the country”
https://www.theguardian.com/us-news/2024/jan/24/americans-believe-israel-committing-genocide-poll
I would still argue ~250 18-29 yo polled is not a great sample size for a population of ~60 million
Is that argument based on mastery of statistics, or intuition? I don’t claim the former for myself, but I distrust the latter in others.
This calculator thingy seems to think it’s pretty representative… https://www.calculator.net/sample-size-calculator.html?type=2&cl2=95&ss2=250&pc2=60&ps2=60000000&x=Calculate#findci
I wouldn’t call myself a master at stats, but maybe learned since I use stats daily as a data engineer. This is called the Small Sample Fallacy and suffers self selection bias (as in, samples are choosing on their own to take the survey).
You put in the wrong numbers, the margin of error is lower, but that’s a moot point because it falls into fallacy.
These are they same fallacies that lead to “every” 2016 election poll saying Hillary was going to win… We all know how that went.