I have a data set of n=98 of values that is normal distributed. This data set has a certain spread and hence a certain standard error of the mean. I now want to test how many samples (ns) I would need to reduce the SEM to a certain value. Could this be done by resampling and if so how would this be done?

  • 1
    $\begingroup$ Because the SEM is proportional to $1/\sqrt{n},$ you can solve this problem in your head: no simulation is needed. You have to assume, of course, that the additional sample will exhibit the same standard deviation as the original sample. So: is it essential that we respond to the part of the question about simulation? $\endgroup$ – whuber Feb 10 at 22:31
  • $\begingroup$ Yes you are completely right. How did I miss that? Thank you very much! $\endgroup$ – Globoquadrina Feb 11 at 8:55

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.