I have the degrees of freedom, difference between means, 95% confidence interval, and p-value of a paired t-test (i.e., a t-test run to analyze pre-post scores). I need to calculate the corresponding correlation coefficient (r).

Do you know any reference indicating how to do so?

  • $\begingroup$ A dependent t-test = a paired t test? The original data is in format (X,Y). Now you have means of D=X-Y, CI of this mean, a p value for testing E(D) = 0, one df. You do not have Variance of X and Y. You want to have r between X and Y. I think it is impossible unless I misunderstood your information or you have more information. $\endgroup$ – user158565 Dec 9 '18 at 19:59
  • $\begingroup$ Could you explain what a "dependent" t-test is? For some versions of t-tests, but not all of them, enough information can be recovered to compute $r.$ $\endgroup$ – whuber Dec 9 '18 at 21:47

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.