[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vip /vp / vr / w / wg / wsg / wsr / x / y ] [Search | Home]
Confidence interval bullshit
If images are not shown try to refresh the page. If you like this website, please disable any AdBlock software!

You are currently reading a thread in /sci/ - Science & Math

File: formula.gif (8 KB, 700x374) Image search: [iqdb] [SauceNao] [Google]
8 KB, 700x374
Let's assume I have a relatively large sample (500) from an unknown distribution. I can calculate sample mean and variance, can I calculate confidence intervals for them? I've googled and found that because of the central limit theorem it should somehow work out for the mean (what distribution would I use in the formula tho? Normal? T?)
Pls help?

>>
https://en.wikipedia.org/wiki/Central_limit_theorem

First. Fucking. Sentence.
>>
>>7788853
kek.

I think you misunderstand the meaning of the CLT.
>>
>>7788853
Relax, if I understood everything I've read I wouldn't post here, would I? I'm shit at stats (and don't really understand confidence intervals), so I was hoping someone could explain this to me. Clearly, you're not the person for the job?

>In probability theory, the central limit theorem (CLT) states that, given certain conditions, the arithmetic mean of a sufficiently large number of iterates of independent random variables, each with a well-defined expected value and well-defined variance, will be approximately normally distributed, regardless of the underlying distribution

Okay, so how does that answer my question? From this I can learn that the average value is approximately normal if I have a large enough sample. Is that sufficient enough reason to use the z table? What about variance/standard deviation?
>>
>>7788773
students t distribution?
>>
>>7788889
Your problem, as you already realize, is that you know nothing about the distribution of the population from which your sample has been selected. Google bootstrapping. You're welcome...
>>
>>7788889
>Is that sufficient enough reason to use the z table

https://en.wikipedia.org/wiki/Normal_distribution

First two paragraphs.

>>
>>7788899
For the variance/deviation? Why not chi square?
>>
Why does everyone here always kick up dust when they can't answer simple questions succinctly? Even if you knew what you're talking about, you're not going to impress some beginner who can't even into CIs with nuanced arguments about assumptions...

Use a t-test because you don't know the population standard deviation.
>>
>>7788946
>t-test
Fucking thank you. You mean Student's t distribution, not t-test (I don't want to test hypotheses), I presume?
Am I to assume these formulas I've found are incorrect?
>>
God I hate statistics. So fucking boring! Thank God I don't have to deal with that shit anymore. Thanks for bringing back the memories and ruining my mood OP!
>>
>>7788993
Misery loves company.