Professor Bobby Duffy, director of the Policy Institute, said the opposing views of some young men and women is a surprising trend. "This is a new and unusual generational pattern," he said.

The reason for the contrasting views of young men and women could be the result of social media consumption. That's the view of Rosie Campbell, Director of the Global Institute for Women's Leadership at King's. She said: "The fact that this group is the first to derive most of their information from social media is likely to be at least part of the explanation."

you are viewing a single comment's thread
view the rest of the comments

[–] FourteenEyes@hexbear.net 8 points 2 years ago* (last edited 2 years ago) (3 children)

Sample size of 3600? That's a fucking rounding error in a proper survey

Edit: apparently i do not understand statistics which is fine

[–] GaveUp@hexbear.net 27 points 2 years ago* (last edited 2 years ago) (1 children)

A properly picked sample size of only 2401 gives you a 2% margin of error on a population of 1 trillion+ people, and if we were to repeat this poll, we would expect 95% of the results would have all answers would fall within this 2% margin of error range

https://www.qualtrics.com/blog/calculating-sample-size/

[–] FourteenEyes@hexbear.net 10 points 2 years ago

disgost this is number witchcraft, begone black magician

[–] SerLava@hexbear.net 27 points 2 years ago (1 children)

I don't think sample size is a problem here at all. That would be a problem if you were trying to detect a tiny change from a previous survey or detect something very rare in a population. But to ensure the accuracy of these numbers within just a couple percentage points, you wouldn't need anywhere close to 3600. It's been a while since I took Stats so I don't remember the particular math for calculating a confidence interval, but if you were trying to find out if say, half the population has brown hair, or a quarter of the population has brown hair, you could figure that out within a few percentage points by checking a random sample of like 20-30ish people.

[–] FourteenEyes@hexbear.net 9 points 2 years ago (1 children)

Admittedly I don't really get the math behind this so I guess I'm talking out my ass. So to rephrase:

After 2020 I will never trust the results of a single poll I see ever again for the rest of my life

[–] SerLava@hexbear.net 7 points 2 years ago

True there are many many other things that they could have done to fuck up the poll

[–] SkingradGuard@hexbear.net 14 points 2 years ago (1 children)

That's fine for a survey lol

[–] FourteenEyes@hexbear.net 6 points 2 years ago (1 children)

i have been owned with facts and logic shapiro-gavel

[–] SkingradGuard@hexbear.net 5 points 2 years ago

kubrick-stare Ignorant leftist OWNT by statistics and LOGICK nerd