If that 10k is representative, that should give a very small uncertainty interval, less than 1%. You can get 95% confidence interval with only a few hundred samples depending on the standard deviation, so 10k is actually massive. It’s pretty standard statistics, here’s more info on how it’s calculated.
That only applies to statistics that follow a nornal distribution. If there’s no bell curve, these numbers don’t make sense.
I don’t know if the distribution is or isn’t shaped well for this kind of statistical analysis, but sample sizes and confidence intervals don’t always work and are sometimes used to distort data.
If that 10k is representative, that should give a very small uncertainty interval, less than 1%. You can get 95% confidence interval with only a few hundred samples depending on the standard deviation, so 10k is actually massive. It’s pretty standard statistics, here’s more info on how it’s calculated.
https://ecampusontario.pressbooks.pub/introstats/chapter/7-5-calculating-the-sample-size-for-a-confidence-interval/
I know jack shit about statics, or this study, but 10K participants seems more than solid if it’s proper science.
That only applies to statistics that follow a nornal distribution. If there’s no bell curve, these numbers don’t make sense.
I don’t know if the distribution is or isn’t shaped well for this kind of statistical analysis, but sample sizes and confidence intervals don’t always work and are sometimes used to distort data.