0
$\begingroup$

I have the following histogram showing a dataset (1200 samples): Histogram

My goal with this, is to say that with a certain confidence, that 90% of all samples are within -0.25ms and +0.25ms. Since it's been a while since I've worked with statistics, I'd like some help.

How do I find that confidence level?

Best regards.

$\endgroup$
0
$\begingroup$

One possibility: Let $X$ be the number of Successes in $n = 2000,$ where a Success is an observation within $\pm 25ms.$ Also, let $P(\text{Success}) =\theta.$ Then $\hat \theta = X/n.$ A 90% confidence interval for $\theta$ is of the form $$\hat \theta \pm 1.645\sqrt{\frac{\hat \theta(1-\hat \theta)}{n}}.$$

Using this in a paper or report, you'd need to explain carefully because you have two intervals, $\pm 25$ms and and the confidence interval for $\theta.$

I have removed the word 'guarantee' from your title, because a confidence interval is hardly a guarantee.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.