I’ve noticed most U.S. polls query around 1,000 people and sometimes even less. Somehow that qualifies for headlines like “Americans say…” or “Most Americans…” How is it acceptable that 0.0002% of the population is accepted as representative?
In: Other
Because statistics say it is enough. If I remember correctly, the minimum sample size for a survey is around 800. That said, it doesn’t mean any survey of 800 people is representative of the country. Your method still has to be good and the samples have to be correct, you can’t just go to one neighborhood of 800 people ask them all a question and say their response is representative of the countr
It depends entirely on statistics and probability. For example, if I look at the relationship between depression and self-compassion in 100 people, I will find the same thing if I asked 1000 people or 10,000 people. More isn’t always better. Sometimes it’s just overkill.
They aren’t. They are clickbait/rage bait headlines. I have to explain this alllllll the time to my coworkers. (POTUS Political example) If you go to a rural community, most surveys are going to favor Trump, always. If you go to a college campus, most surveys are going to trend progressive. If you go to an elementary school, most surveys are going to favor Bluey or Ryan.
The “news media” just picks their favored region and takes a poll from there.
You actually only need 385, if they’re a proper representative sample for a 5% margin of error.
Many people struggle to grasp how statistics works, and are surprised when numbers don’t match their intuition. Like how given 23 random people there’s a 50/50 chance of two people having the same birthday, or 75 random people there’s a 99.9% chance of two people matching. However, if the population isn’t random then different rules apply, like a sampling of a gathering where the people are meeting for a leap-day birthday.
With polling, there is the confidence level and the margin of error that are critical. For a large group like the US, if you ask a representative cross section of people you don’t need tremendous numbers of samples. You can’t ask in a single neighborhood or a single demographic and expect it to represent the nation, but if you’re careful in who you ask it quickly reveals the national trends with relatively few survey samples.
The tighter you want the margin of error the more samples you need. Just 25 people gives a 20% margin of error. 43 people give a 15% margin of error. 97 people gives a 10% margin of error, which is good enough for many surveys. To jump to 5% margin of error you need about 385 people, and a 3% margin of error needs 1068 people. Those are typically what you see in big elections. For very close elections, a 2% margin of error takes 2401 samples, and 1.5% needs 4269 people, 1% needs 9604 people, it’s quite rare for surveys to reach that level.
For elections very often the spread is big enough you only need about 50 or 100 people, more than enough for the trend to be clear. For very close elections a 5% margin might be needed. If they candidates really are at 3% difference, like it has been in a few extremely close national elections, they need a lot of samples to become that much more precise.
I’m just not sure whether people who answer polls self-select. It’s impossible to know whether an invitation to do a poll is malicious or not.
The biggest issue lately isn’t actually the small sample size. The reason surveys are getting more unreliable is because younger people are much less likely to pickup the phone when they don’t recognize the number.
If your sample set is representative of the total population and is significantly large enough, then you can extrapolate sample results like that. There will be some statistical error, but you can make statements with a mathematically determined certainty.
Well first of all you can never ask all of America a question, or even half of it. So when you see an article with a headline like “Americans oppose xyz” is there really any danger of anyone thinking that the entire population was questioned?
You might say of course not, it’s ridiculous to question the whole country and you don’t need to. But if you accept that any subset of the group can be sampled to study the whole, then it’s a simple matter of statistics. You can detect trends of a certain magnitude with a certain confidence, from asking 1000 people. And the additional precision you’d get from dialing that up to 10,000 people is not worth 10x the effort.
Adults understand that polls are polls and articles are up front when they are reporting the results of a poll, just maybe not always in the headline.
Latest Answers