I want to calculate a standard error of a sample. I have a distribution of the IQ of the general population with a mean of 100 and a standard deviation of 19. Now I take a random sample of 30 students of Harvard and find that their mean IQ is 125.

I want to calculate the standard error of the mean. How can I do this? I cannot use $\sigma \over \sqrt{n}$ because I don't have the sd of my sample or?

  • 1
    $\begingroup$ You need the sample standard deviation $\hat{\sigma}$ to estimate the standard error. $\endgroup$ – user2974951 Sep 26 '18 at 12:06
  • $\begingroup$ Yes, thats what I thought. We don't have that. Is there another way like bootstrapping? $\endgroup$ – Jensxy Sep 26 '18 at 12:18
  • $\begingroup$ You can only do bootstrap if you have a sample, which you don't, otherwise you could estimate the SD. $\endgroup$ – user2974951 Sep 26 '18 at 12:20
  • $\begingroup$ I also know that the IQ is normal distributed. That's it. That are all information in the question. $\endgroup$ – Jensxy Sep 26 '18 at 14:53
  • $\begingroup$ Then you are figuratively screwed. $\endgroup$ – user2974951 Sep 27 '18 at 6:02

Your Answer

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

Browse other questions tagged or ask your own question.