0

I have a very basic question regarding confidence intervals. I am confused between two interpretations of confidence intervals.

Interpretation 1:

If repeated samples were taken and the 95% confidence interval computed for each sample, 95% of the intervals would contain the population mean.5% of the intervals would not contain the population mean

Interpretation 2: If we were to take 100 additional samples, 95 times out of 100, the population mean rate would fall between 2.5% and 17.5%.

Which of these would be correct?

Rajarshi Bhadra
  • 165
  • 2
  • 9
  • Maybe the section 3. of this answer will help you: http://stats.stackexchange.com/questions/167972/why-is-there-a-need-for-a-sampling-distribution-to-find-confidence-intervals/167998#167998 –  Aug 23 '15 at 09:03
  • Thank you. This is exactly what I was looking for. From that it seems to me that the first implication is correct – Rajarshi Bhadra Aug 23 '15 at 09:12
  • I agree with you, don't thank me, but vote for my answer I referred to if you think it helped you –  Aug 23 '15 at 09:15
  • Also see discussion [here](http://stats.stackexchange.com/questions/11609/clarification-on-interpreting-confidence-intervals) and [here](http://stats.stackexchange.com/questions/138528/does-a-confidence-interval-actually-provide-a-measure-of-the-uncertainty-of-a-pa/138546#138546) and [here](http://stats.stackexchange.com/questions/104499/what-is-the-most-likely-meaning-of-a-confidence-interval/104564#104564) – Glen_b Aug 23 '15 at 09:35

0 Answers0