I have difficulties in calculating confidence interval using Jackknife. Suppose that I have two independent samples and I do not know both their population distributions.

I understand how to calculate the confidence interval of $\mu_x-\mu_y$, but I have no idea of how to calculate the confidence interval of $\mu_x/\mu_y$.

I think applying delta method is invalid since I can not guarantee that the two samples are from normal distribution.

  • 2
    $\begingroup$ This might help you. $\endgroup$ – Lucas Farias Feb 8 '19 at 16:27
  • $\begingroup$ You should note that $\mu_x$-$\mu_y$ looks different from $\mu_x-\mu_y,$ and the latter is the proper way to do it. Just type a dollar sign and then don't type another until you get all the way through the mathematical notation that you're typing. $\endgroup$ – Michael Hardy Feb 9 '19 at 1:50

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.